=Paper=
{{Paper
|id=Vol-3814/paper5
|storemode=property
|title=Tracing the Palola Shahi Royal Genealogy by Fusing LLMs and Databases?: A Case Study
|pdfUrl=https://ceur-ws.org/Vol-3814/paper5.pdf
|volume=Vol-3814
|authors=Hui Xu,Thomas Asselborn,Haiyan Hu-von Hinüber,Oskar von Hinüber,Sylvia Melzer
|dblpUrl=https://dblp.org/rec/conf/chai/XuAHHM24
}}
==Tracing the Palola Shahi Royal Genealogy by Fusing LLMs and Databases?: A Case Study==
https://ceur-ws.org/Vol-3814/paper5.pdf
Tracing the Pal.ola S.āhi Royal Genealogy by Fusing LLMs
and Databases?: A Case Study
Hui Xu1 , Thomas Asselborn1,2 , Haiyan Hu-von Hinüber3,4 , Oskar von Hinüber5 and
Sylvia Melzer1,2,6
1
University of Hamburg, Institute of Humanities-Centered AI (CHAI), Warburgstraße 28, 20354 Hamburg, Germany
2
University of Hamburg, Cluster of Excellence ‘Understanding Written Artefacts’ (UWA), Warburgstraße 26, 20354
Hamburg, Germany
3
Max-Weber-Kolleg, Steinplatz 2, 99085 Erfurt, Germany
4
Shandong-Universität, Shanda-Nanlu 27, 250100 Jinan, China
5
Akademie der Wissenschaften und Literatur, Geschwister-Scholl-Str. 2, 55131 Mainz, Germany
6
University of Hamburg, Centre for the Study of Manuscript (CSMC), Warburgstraße 26, 20354 Hamburg, Germany
Abstract
In this article, we explore an innovative approach to reconstruct the genealogy of the royal family Pal.ola S.āhi
dynasty by combining Large Language Models (LLMs) with traditional database systems. The research aims
to demonstrate how the fusion of various LLMs and structured historical data can enhance our understanding
of complex genealogical relationships in historical families. The methodology involves using the contextual
understanding and inference abilities of LLMs, such as GPT-3.5 Turbo, Mistral Instruct, to interpret and enhance
historical information stored in relational databases. By combining these two data sources, the study seeks to
identify patterns, fill gaps, and generate new insights into the Pal.ola S.āhi lineage. This article addresses challenges
such as reconciling conflicting information, handling uncertainties, and maintaining historical accuracy while
utilizing agents such as Perplexity.ai, ChatGPT, UHHGPT, and GPT4All to generate inferences. The case study of
the Pal.ola S.āhi royal family serves as a practical demonstration of this hybrid approach, showcasing its potential
to enrich historical research. The findings not only contribute to a more comprehensive understanding of this
specific dynasty but also provide a framework for applying similar methods to other genealogical studies in
historical research. This research highlights the potential of interdisciplinary approaches in the humanities.
1. Introduction
The Gilgit bronze inscriptions, which refer to the Pal.ola S.āhis royal family, provide valuable insights
into Buddhist culture and patronage in the Gilgit region during the 6th to 8th centuries. [1] The earliest
known datable bronze produced under the Pal.ola S.āhis’ patronage precedes Navasurendätiya’s bronze
of AD 644 (or 655) by over twenty years, and surpasses the age of the third ruler Surendräditya’s work
by at least ten years. [2] The bronzes often feature dedicatory inscriptions in Sanskrit, written in a script
characteristic of northwest India during that period. The inscriptions on Buddhist statues from the
period of the Pal.ola S.āhi dynasty can provide valuable insights into the genealogy of the royal family.
These inscriptions often include the names and titles of the donors, who were frequently members of
the royal family. For instance, inscriptions have recorded dignitaries such as Śrı̄ Surabhı̄ in 678/679
CE, Princess Devasrı̄ in 714 CE, and King Nandivikramadityanandi in 715 CE (see Figure 10, Figure 6,
and Figure 9 in [3]). These figures are often depicted as donors at the base of the statues, along with
identifying inscriptions.
Humanities-Centred AI (CHAI), 4th Workshop at the 47th German Conference on Artificial Intelligence, September 23, 2024,
Würzburg, Germany
*
Hui Xu
$ hui.xu@studium.uni-hamburg.de (H. Xu); thomas.asselborn@uni-hamburg.de (T. Asselborn);
sylvia.melzer@uni-hamburg.de (S. Melzer)
https://www.uni-hamburg.de (H. Xu); https://www.philosophie.uni-hamburg.de/chai/personen/asselborn.html
(T. Asselborn); https://www.csmc.uni-hamburg.de/about/people/melzer.html (S. Melzer)
0009-0001-2474-275X (H. Xu); 0009-0005-3011-7626 (T. Asselborn); 0000-0002-5284-9001 (H. Hu-von Hinüber);
0000-0002-0144-5429 (S. Melzer)
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
Tracing the genealogy of a historical royal family solely on the basis of inscriptions on statues and the
few manuscripts available is a laborious task that presents many challenges. The lack of reliable sources
and the risk of misinterpretation make the undertaking difficult for researchers. Nevertheless, dedicated
humanities scholars have taken on this daunting challenge and tackled it with meticulous attention
to detail and unwavering determination. These researchers have embarked on an arduous journey to
examine each piece of evidence with the utmost care. They carefully analyse each artefact, inscription
and manuscript and piece together the fragments of information into a coherent story. Through interdis-
ciplinary approaches and the use of advanced techniques in fields such as epigraphy, palaeography and
archaeology, these scholars attempt to extract every possible clue from the limited resources available.
In their work, they not only decipher ancient texts and symbols, but also compare the results with other
historical records and archaeological finds. In this way, they attempt to reconstruct the history of the
royal family using verifiable facts and tangible artefacts. By meticulously connecting the dots between
different pieces of evidence, these researchers are gradually creating a framework for understanding
the genealogical connections within royal families. While this task remains challenging and often
fraught with speculation, the dedication of these humanities scholars ensures that our understanding of
historical royal genealogies is constantly evolving and improving. Their efforts contribute significantly
to our knowledge of the past and shed light on the complicated web of relationships that shaped the
ruling dynasties of past eras.
In the field of humanities research, scholars typically record their collected data in documents or
information systems [4, 5]. While relationships between the data sets can be established, it is often
impossible to represent all potential combinations of connections. Drawing inspiration from advanced
AI techniques like FuseLLM [6], we propose an innovative approach to genealogical research that aims
to construct more comprehensive family histories. This method aims to uncover hidden connections
and expand our understanding of lineages by bringing together information from different sources,
such as those from different agents.
Our research question can be formulated as follows: How can we effectively integrate a LLM (Large
Language Model) with diverse database contents to reconstruct and enrich the genealogy of a family, using
the royal Pal.ola S.āhi dynasty as a case study?
2. Genealogy of the Pal.ola S.āhi family
In the following two subsections, we give an overview about the current state/knowledge of the
genealogy of the royal family Pal.ola S.āhi.
2.1. Genealogy created by Experts
In the article [7] an overview about the relations between kings, queens, sons, and daughters are given.
In Table 1 the relationships between kings and queens are presented.
We can regard this information from article [7] and Table 1 as ground truth, as these statements have
been meticulously investigated and substantiated.
2.2. Genealogy created by Agents
We first determined the genealogy of the known and current kings and queens with the help of some
agents (ChatGPT and Perplexity.ai). The results were correct. Now we had chosen the approach of using
agents for unknown family trees to see how the LLM copes with genealogies that are not well known
and available in the trained LLM material. Therefore, we have used the following agents with different
language models and tried to obtain further information about the royal family tree: Perplexity.ai1 ,
1
https://www.perplexity.ai/
King Queen Reign
ŚĪLĀDITYANANDIN - ca. 532 AD
SOMANA - 6th century
1. Śrı̄ Paramadevı̄ Mam . galaham . sikā
VAJRĀDITYANANDIN 585 - 605 AD
Bhat.t.ārikā
2. Śrı̄ Torabhat.t.ārikā
VIKRAMĀDITYANANDIN 1. Śrı̄ Paramadevı̄ Toraham . sikā 605 - 625 AD
2. Śāmı̄devı̄ Saharan.amālā
3. (Mahā)Devı̄ Surendra(mālā)
Bhat.t.ārikā
4. (Mahā)Devı̄ Di+ysāpun.yā
5. uvakhı̄ Śrı̄ Mahādevı̄ Dilditapun.yā
[6. Jayaprabhat.ā]
SURENDR(AVIKRAM)ĀDITYANANDIN 1. Śāmı̄devı̄ Trailokyadevı̄ Bhat.t.ārikā 625 - 640/655 AD
2. Śrı̄ Śāmidevı̄ Saran.amālā
3. Śrı̄ Mahādevı̄ Salān.ahansikā
[4. Śrı̄ Mahādevı̄ Jayaprabhat.ā] (possi-
bly)
[(Sam
. )Pūrn.ādityanandin - 640 - 655]
NAVASURENDR(A/ĀDITYANANDIN) ̇
1. Śrı̄mad Anangadevı̄ 644/655 - 685 AD
2. Rājñı̄ Rāmamālā (?)
̇
JAYAMANGALAVIKRAMĀDITYANANDIN 1. Śāmadevı̄ Śāmāvatı̄ 685 - 710 AD
̇
2. Mahādevı̄ Mangalakesarı̄
NANDIVIKRAMĀDITYANANDIN Śrı̄ Śāmı̄devı̄ Namobuddhāya 710 - 715 AD
[Su-fu-she-li-chi-li-ni - 715 - 720 AD
= Nandivikramādityanandin?
*SURENDRĀDITYA - 720 AD - ?
Table 1
Pal.ola S.āhi rulers and their reigns defined by Luo Wenhua and Oskar von Hinüber [7]
UHHGPT2 (model: GPT-3.5 Turbo), ChatGPT3 (model: GPT-4o), GPT4all4 (model: Mistral Instruct; w/o
internet connection). We have commented on every answer unless it was obvious. The input documents
for GPT4All are the following technical reports: [8, 9, 10, 11, 12, 13].
Question 1: Please give me an overview of the genealogy of the royal family Palola Shahi.
Answer 1: Perplexity.ai The Palola Shahi dynasty ruled the kingdom of Balur (also known as Palola
or Bolor) in the Gilgit region of present-day northern Pakistan from approximately the 7th to the early
8th century CE. [. . .] Unfortunately, the search results do not provide a comprehensive genealogy or
list of all the rulers of the Palola Shahi dynasty. The information available is limited, likely due to the
scarcity of historical records from this period and region.
Comment: Perplexity.ai does not deliver any information about the genealogy of the royal family. In
addition, the more appropriate definition would be: The royal family Pal.ola S.āhi belonged to a dynasty
of Buddhist kings in the Gilgit kingdom in the northern part of the Indian subcontinent in the 6th-8th
centuries. The names Balur, Palola, Patola, and Bolor refer to the same kingdom.
Answer 1: ChatGPT ChatGPT’s answer is represented in Table 2.
2
https://uhhgpt.uni-hamburg.de/
3
https://chatgpt.com/
4
https://gpt4all.io/
King Reign
Deva Shahi Mid-7th century CE
Navasurendrāditya Nandi Early 8th century CE
Vajradhara Indra Pala Late 8th century CE
Sri Deva Palola Shahi Early 9th century CE
Table 2
ChatGPT’s answer of Question 1
Comment: ChatGPT’s answer presumably has other names of the kings. In [14] the king Vajra-
dityanandi has the identified title Sri Patola Deva Sahi. ChatGPT presents the short name “Deva Shahi.”
The king Navasurendradityanandi has the identified title “Paramabhattaraka Maharajadhiraja Parames-
vara Patola Deva Shahi Sri Navasurendradityanandi Deva.” ChatGPT presents his name in another
writing style, namely Navasurendrāditya Nandi. Vajradhara Indra Pala did not exist and is probably
a mixture of two names. There was a king named Indra Pala who ruled the Kamarupa Kingdom as
part of the Pala Dynasty from 960-990 CE. [15] This Indra Pala was a historical figure, but he is not
associated with the name Vajradhara. Vajradhara is a primordial Buddha figure in Tibetan Buddhism,
representing the essence of the Buddha’s enlightenment. [16] Jayamangalavikramadityanandi styled
himself as “Maharajadhiraja Paramesvara Shahanu Shahi Palo1a Shahi Sri Deva.” [15] ChatGPT presents
his name as “Sri Deva Palola Shahi.”
Answer 1: UHHGPT I’m sorry, but there seems to be a misunderstanding. As far as my knowledge
goes, there is no record or mention of a royal family by the name of Palola Shahi. [. . .]
Comment: UHHGPT does not deliver an answer of question 1 because of the missing data in the
LLM.
Answer 1: GPT4All using Mistral Instruct The Palola Shahi were a royal dynasty that ruled over
parts of modern-day Pakistan and India during the medieval period. They originated from the city of
Palola in what is now Punjab, Pakistan, and their name means “Lord of Palola.”
The genealogy of the Palola Shahi can be traced back to Rājad.i Tejad.i, who was a noble lady and
possibly also the sister of Rājad.i. Another member of the ruling family was bhāryā Jı̄jad.i, whose name
means “daughter of Jı̄jā.” [. . .]
Comment: GPT4All gives an overview about the kingdom and some familiar information. A check
of the answer with other sources has shown that this information is not correct.
Question 2: Please give me an overview of the genealogy of the royal family Palola Shahi. Consider:
https:// en.wikipedia.org/ wiki/ Patola_Shahis.
Answer 2: Perplexity.ai The Patola Shahis, also known as the Palola Shahis or Gilgit Shahis, were
a Buddhist dynasty that ruled the Kingdom of Gilgit in the northern Indian subcontinent from the
6th to the 8th century CE. The genealogy of the Patola Shahi dynasty is documented through various
inscriptions and historical records. [. . .]
Comment: The genealogy provided in this table is basically the same as that provided in the ge-
nealogy defined by Luo Wenhua and Oskar von Hinüber. The differences are as follows. First, King
ŚĪLĀDITYANANDIN (reign ca. 532 AD) is not mentioned, and King SOMANA’s reign time is listed as
the mid-6th century instead of the 6th century. Second, the crown prince (Sam
. )Pūrn.adityanandin of
King SURENDR(AVIKRAM)ĀDITYANANDIN is not mentioned in Table 3. It is not clear whether or not
he ever ruled. Third, the reign time of the last King SURENDRĀDITYA is given as 720-740 or 750 CE,
Ruler Reign
Somana Mid-6th century CE
Vajraditayanandin 585-605 CE
Vikramadityanandin 605-625 CE
Surendravikramadityanandin 625-644 or 654 CE
Navasurendrāditya-nandin 644 or 654-685 CE
̇
Jayamangalavikramāditya-nandin 685-710 CE
Nandivikramadityanandin 710-715 CE
Su-fu-che-li-chi-li-ni 715-720 CE
Surendradityanandin 720-740 or 750 CE
Table 3
Perplexity.ai’s answer of Question 2
while it is only mentioned as starting from 720 CE in the genealogy defined by Luo Wenhua and Oskar
von Hinüber. In addition, queens are not mentioned in Table 3.
Answer 2: UHHGPT I apologize for the confusion, but it seems that there is an error in your request.
The link you provided redirects to a page about “Patola” instead of “Palola” Shahis. Unfortunately, there
is no specific information available on the Palola Shahi royal family.
However, if you are looking for information on other royal families or have any other questions
related to genealogy or history, please feel free to ask. I would be happy to help you with that.
Answer 2: ChatGPT ChatGPT delivers an overview about kings from another dynasty, e. g. Shahi
Tegin.
Answer 2: GPT4All with Mistral Instruct [. . .] The genealogy of the royal family Palola Shahi can
be traced back to Rājad.i Tejad.i, who was a noble lady and perhaps also a member of the ruling family.
She had two daughters: Sara and bhāryā Jı̄jad.i. Sara’s son, Ajitasena, became the first known ruler of
Palola in 1290.
Ajitasena had several sons who also ruled as kings of Palola, including Rājad.i Tejad.i II and
bhāryā Jı̄jad.i II. The dynasty continued to rule for several centuries, with notable rulers such as
Man.galavikramādityanandi and Rājād.i Tejad.i III. [. . .]
1. Date: 2024, June 13. In Vol. XX (2017).pdf. Page 136.
2. Date: 2024, June 13. In Vol. XXI (2018).pdf. Page 6.
3. Date: 2024, June 13. In Vol. XXI (2018).pdf. Page 8.
Question 3: Please give me an overview of the genealogy of the royal family Patola Shahi. Consider:
https:// en.wikipedia.org/ wiki/ Patola_Shahis
Answer 3: UHHGPT I’m sorry, but I can’t provide specific information on the genealogy of the
Patola Shahi royal family from the link you provided because the Patola Shahis are a fictional royal
family from the TV series “The Blacklist.”
Question 4: Please give me an overview of the genealogy of the royal family Palola Shahi. Please
mention all the queens of each king, his sons, his daughters, the mother and father of the king.
Answer 4 (excerpt): Perplexity.ai The ruler Vajraditayanandin (585-605 CE) was married with the
queen Mangalahamsika. This sentence presents the additional information about the mentioned queen.
The same kings as presented in Table 1 are part of Perplexity.ai’s answer.
Comment: Perplexity.ai delivers a part of the queen’s name “Mangalahamsika” written with the
letter “n” instead of m
..
Answer 4 (excerpt): ChatGPT ChatGPT’s answer of question is presented in Table 4.
King Father Son
Navasurendrāditya-nandin Supratis.t.hitavarman Supratis.t.hitavarman II
Supratis.t.hitavarman II Navasurendrāditya-nandin Kumārāja
Kumārāja Supratis.t.hitavarman II Jayavarman
Jayavarman Kumārāja Lalitāditya
Lalitāditya Jayavarman -
Table 4
ChatGPT’s answer of question 4: Kings, along with their fathers and sons, are mentioned, while queens and
daughters are omitted
Comment: This information is irrelevant because the kings mentioned in Table 4 are from another
dynasty and partly incorrect. For example, Supratis.t.hitavarman ruled Kamarupa from the Varman
dynasty for the period 595–600. He was son of King Susthitavarman and Queen Shyamadevi. [17]
Answer 4: GPT4All using Mistral Instruct [. . .] The Palola Shahi dynasty was founded by
Nāmasim. ha (1250-1300), who is considered as the first king of the Palola Shahi. He had four queens: Di
+ (ysa)pun.yā, Rājñı̄ Tejad.i, Rājad.i, and Bhāryā Jı̄jad.i. Nāmasim
. ha had two sons, Sara and Yudhajit, and
one daughter, Devalaks.mi. [. . .]
Question 5: Please give me an overview of the genealogy of the king SOMANA of the royal family Palola
Shahi. Please mention all the queens of the king, his sons, his daughters, the mother and father of the king.
Answer 5: ChatGPT
• King Somana: father → Devaśāntika; queens → Śrı̄ Prabhāvatı̄ (main queen, as per historical
inscriptions); sons → Somila (mentioned in historical records as a son and successor); possibly
other sons, but not clearly mentioned in available records. [. . .]
• Queen: Śrı̄ Prabhāvatı̄: children with Somana → Somila (son and successor); son → Somila; father
→ Somana; mother→ Śrı̄ Prabhāvatı̄
Comment: In contrast to Luo Wenhua’s and Oskar von Hinüber’s researches, there’s no information
about King Somana’s queens. The name Śrı̄ Prabhāvatı̄ appears in the context of verses (cf. [18]).
Answer 5: GPT4All using Mistral Instruct King Somana was a member of the royal family Palola
Shahi, which is one of the most prominent families in medieval India. The genealogy of the Palola Shahi
family can be traced back to Soma Deva, who was the founder of the dynasty. [. . . ]
Somabhadra had two sons: Somakrishna and Somaditya. Somakrishna’s son was Somanath, who
was the father of King Somana. Therefore, King Somana was a descendant of Soma Deva through his
great-grandfather, Somadeva.
King Somana had two sons: Somasimha and Somaditya. Somasimha’s son was Somanath, who was
the father of King Somapala. Therefore, King Somana was also a descendant of Soma Deva through his
great-grandson, Somadeva.
King Somana had two daughters: Somavati and Somakrishna. The identity of their mothers is not
mentioned in any historical records.
1. Date: 2024, June 13. In Vol. XVIII (2015).pdf. Page 263.
2. Date: 2024, June 13. In Vol. XVIII (2015).pdf. Page 368.
3. Date: 2024, June 13. In Vol. XXI (2018).pdf. Page 502.
Comment: The information presented by GPT4All about the king Somana not be found in Vol. XVIII
(2015) (page 263, 368) and Vol. XXI (2018) (page 502). The answer given by GPT4All must therefore be
verified by other sources.
Question 6: Please give me an overview of the genealogy of the king VAJRĀDITYANANDIN of the
royal family Palola Shahi. Please mention all the queens of the king, his sons, his daughters, the mother
and father of the king.
Answer 6: ChatGPT
• King Vajrādityanandin: father → Navasurendrāditya-nandin; son → Nandivikramādityanandin
(likely successor)
• Father: Navasurendrāditya-nandin: father → Supratis.t.hitavarman; children → Vajrādityanandin
(son, and eventual king); possibly other children, but not clearly mentioned in available records.
• Son: Nandivikramādityanandin; father → Vajrādityanandin
Comment: ChatGPT’s answer is not correct. The King Vajrādityanandin could not be the son of
Navasurendrāditya-nandin because Navasurendrāditya-nandin ruled later (cf. Table 1). The son’s name
of the king Navasurendradityanandi was Jayamaṅ galavikramādityanandi (cf. Table 1).
Answer 6: GPT4All using Mistral Instruct The genealogy of King Vajrādityanandin of the Royal
Family Palola Shahi is as follows:
• Father: Maharaja Nāmasim . ha (1)
• Mother: Queen Di + (ysa)pun.yā (2)
• Sons: Prince Rājñı̄ Tejad.i (3), Prince Sara (4)
• Daughters: Princess Bhāryā Jı̄jad.i (5) [. . .]
1. Date: 2024, June 13. In Vol. XX (2017).pdf. Page 136.
2. Date: 2024, June 13. In Vol. XX (2017).pdf. Page 136.
3. Date: 2024, June 13. In Vol. XX (2017).pdf. Page 140.
Comment: GPT4all delivers the name Di + (ysa)pun.yā as the mother of the king Vajrādityanandin,
but she was the 4th queen of the king Vikramadityanandin, the successor of Vajrādityanandin. The
other results could not be confirmed. This information can not be found in Vol. XX (2017) (page 136,
140).
2.3. Genealogy Representation in Information Systems
Heurist Heurist [19] is a user-friendly data management system designed specifically for humanities
researchers. While it excels in handling smaller datasets, particularly in humanities-related projects, its
effectiveness with large datasets may be limited [5]. Heurist allows researchers to design, populate,
explore, and publish richly-structured databases through a simple web interface, without requiring
extensive technical expertise. [20]
After manually or automatically transferring data to a Heurist database instance, networks can
be displayed at the touch of a button using the available functionality. In Figure 1 an excerpt of the
historical people are presented based on the data from Table 1.
Figure 1 shows which persons have a relationship to another person. The type of relationships is not
shown in the figure but are stored in the database instance of Heurist. It is possible to display networks
that only have a mother-child, father-child relationship or other relationships.
Figure 1: Network of the collected data about historical people created with Heurist
PouchDB PouchDB [21] is a powerful and versatile open-source JavaScript database that offers
unique advantages for handling large datasets, particularly in web-based applications. As a client-side
database inspired by Apache CouchDB [22], PouchDB stores data in JSON format and implements the
Couch Replication Protocol, enabling seamless synchronization between local instances and CouchDB
servers. One of PouchDB’s key strengths is its ability to work offline, storing data locally in the browser’s
Web storage, such as IndexedDB [23] in Firefox. This “Offline First” approach allows users to work
with their database without an internet connection, in contrast to Heurist, making PouchDB ideal for
researchers and analysts who need constant access to their data. PouchDB’s architecture eliminates the
need for additional server-side resources, reducing infrastructure complexity and costs. Its flexibility in
generating HTML pages and customizing database queries makes it particularly appealing to humanities
scholars who require adaptable data representation tools. In Figure 2 an information system created
with PouchDB is presented. The data from Table 1 are represented in a searchable table. In the first
column of the table, the people’s names are presented. In the fourth column (related person(s)), relations
from the persons in column one to other people are presented.
An improved implementation can incorporate the specific type of relationship between individuals,
such as son of, mother of, etc. This approach offers several advantages over the simpler table structure
shown in Figure 2.
3. Fusion of LLMs and Databases
Our methodology draws inspiration from the FuseLLM approach, but introduces key distinctions. Our
approach extends beyond mere LLM fusion, incorporating content from diverse databases and agents
to enrich the knowledge base. Our suggested fusion process is as follows:
• We use different agents with (different LLMs). An agent with its LLM computes the best text
(list of relations between kings and queens) as an answer. These answers should give more
Figure 2: Information System created with PouchDB
information for a dataset represented in a relational database.
• The information about the royal family are stored as datasets in a relational database.
• An expert can add the new information (the agents’ answers) to a dataset. In the hope of gaining
new and correct(!) insights.
In [6] a collective knowledge matrix is calculated in order to visualise the results of the individual
agents in their entirety. In our approach, we imagine that this matrix is supplemented by further entries
that originate from the information systems for the representation of collective knowledge.
Application and Results In the concrete implementation of the fusion approach, we visualized the
data using either Heurist or PouchDB. We developed prototypes for both to explore how to integrate
or combine database representations with the agents’ responses. While Heurist offers a similar table
view to PouchDB, we found that PouchDB performs better with larger datasets and provides offline
functionality.
At the start, we first tried to obtain information about the entire repository, i.e. the genealogy of the
Pal.ola S.āhi royal family. The answers and our comments show that these were rather wrong and could
not be considered. We have therefore tried to be more specific with the names. But if you enter all
names - i.e. all data records with kings - and want the answers from the LLMs, we found that only the
names of kings also from other dynasties and the reigns were returned. It was interesting, however,
that the names of some kings were alternative names and the answers could be taken into account as
an additional source. Although these additional sources could not provide any clues to the family tree,
they could be helpful for other research questions.
As a result, we were able to compile the family tree of the royal family Pal.ola S.āhi, whereby no new
findings could be provided by the agents in our research.
Figure 3: Family tree of the royal family Pal.ola S.āhi.
This almost expected result was probably due to the fact that there is too little training material
on this royal family. Even if it did not help with the identification of the family tree, the additional
information and the sources found can be helpful in creating a general overview of a topic.
It was not possible to carry out an evaluation as with the FuseLLM [6] approach with this data set.
Further investigations are required to check whether the expansion of the knowledge base to include
data from the information systems leads to better results.
4. Conclusion and Outlook
In this article, we present an innovative approach to reconstruct the genealogy of the royal family
Pal.ola S.āhi by combining LLMs with traditional database systems. The study aimed to enhance our
understanding of complex genealogical relationships in historical families by using the contextual
understanding and inference abilities of LLMs, such as GPT-3.5 Turbo and Mistral Instruct, along with
structured historical data stored in relational databases.
The case study of the Pal.ola S.āhi family served as a practical demonstration of this hybrid approach,
showcasing its potential to enrich historical research. However, we found that the agents’ answers were
often wrong and could not be considered reliable. We then tried to be more specific with the names,
but the results were limited to the names of kings from other dynasties and their reigns. While the
additional sources found could not provide any clues to the family tree, they could be helpful for other
research questions. The researchers were ultimately able to compile the family tree of the Pal.ola S.āhi
family using traditional methods, without any new findings from the used agents.
Funding Information
The research for this contribution was funded by the Deutsche Forschungsgemeinschaft (DFG, Ger-
man Research Foundation) under Germany’s Excellence Strategy - EXC 2176 ’Understanding Written
Artefacts: Material, Interaction and Transmission in Manuscript Cultures’, project no. 390893796. The
research was mainly conducted within the scope of the Centre for the Study of Manuscript Cultures
(CSMC) at Universität Hamburg.
References
[1] Wikipedia contributors, Patola shahis, Wikipedia, The Free Encyclopedia, 2024. URL: https://en.
wikipedia.org/wiki/Patola_Shahis, accessed June 25, 2024.
[2] O. von Hinüber, Die Palola s.āhis: Ihre Steininschriften, Inschriften auf Bronzen, Handschriftenkolo-
phone und Schutzzauber: Materialien zur Geschichte von Gilgit und Chilas, Antiquities of
Northern Pakistan, Heidelberg Academy of Sciences and Humanities, Mainz, 2016. URL: https:
//d-nb.info/1123441529/34.
[3] R. L. Twist, Images of the crowned buddha along the silk road: Iconography and ideology,
Humanities 7 (2018). URL: https://www.mdpi.com/2076-0787/7/4/92. doi:10.3390/h7040092.
[4] S. Schiff, S. Melzer, E. Wilden, R. Möller, TEI-Based Interactive Critical Editions, in: S. Uchida,
E. Barney, V. Eglin (Eds.), Document Analysis Systems, Springer International Publishing, Cham,
2022, pp. 230–244.
[5] S. Melzer, S. Schiff, F. Weise, K. Harter-Uibopuu, R. Möller, Databasing on demand for research
data repositories explained with a large epidoc dataset, in: CENTERIS 2022 - Conference on
ENTERprise Information Systems, SciKA, 2023, pp. 150–153.
[6] Y. Gu, M. Dong, M. Liu, O. Koyejo, J. Zhao, S. Liang, Llm augmented llms: Expanding capabilities
through composition, arXiv preprint arXiv:2401.10491 (2024).
[7] W. Luo, O. von Hinüber, News from palola: The jokhang and the yong-he inscriptions of
surendrāditya, in: N. Kudo (Ed.), Śāntamatih. - Manuscripts for Life, volume 15 of Bibliotheca
Philologica et Philosophica Buddhica, International Research Institute for Advanced Buddhology,
Soka University, Tokyo, 2023, pp. 207–223.
[8] International Research Institute for Advanced Buddhology, Annual Report of the International
Research Institute for Advanced Buddhology at Soka University, Annual Report, Soka University,
2014. URL: https://iriab.soka.ac.jp/content/pdf/aririab/Vol.%20XVII%20(2014).pdf.
[9] International Research Institute for Advanced Buddhology, Annual Report of the International
Research Institute for Advanced Buddhology at Soka University, Annual Report, Soka University,
2014. URL: https://iriab.soka.ac.jp/content/pdf/aririab/Vol.%20XVII,%20Supplement%20(2014).pdf,
supplement.
[10] International Research Institute for Advanced Buddhology, Annual Report of the International
Research Institute for Advanced Buddhology at Soka University, Annual Report, Soka University,
2015. URL: https://iriab.soka.ac.jp/content/pdf/aririab/Vol.%20XVIII%20(2015).pdf.
[11] International Research Institute for Advanced Buddhology, Annual Report of the International
Research Institute for Advanced Buddhology at Soka University, Annual Report, Soka University,
2015/2016. URL: https://iriab.soka.ac.jp/content/pdf/aririab/Vol.%20XVIII%20(2015)A______Vol.
%20XIX%20(2016)%20Texts.pdf, texts.
[12] International Research Institute for Advanced Buddhology, Annual Report of the International
Research Institute for Advanced Buddhology at Soka University, Annual Report, Soka University,
2017. URL: https://iriab.soka.ac.jp/content/pdf/aririab/Vol.%20XX%20(2017).pdf.
[13] International Research Institute for Advanced Buddhology, Annual Report of the International
Research Institute for Advanced Buddhology at Soka University, Annual Report, Soka University,
2018. URL: https://iriab.soka.ac.jp/content/pdf/aririab/Vol.%20XXI%20(2018).pdf.
[14] Kreately, Palola shahis of gilgit, https://kreately.in/palola-shahis-of-gilgit/, 2024. URL: https://
kreately.in/palola-shahis-of-gilgit/, accessed June 27, 2024.
[15] Wikipedia contributors, Indra pala, 2024. URL: https://en.wikipedia.org/wiki/Indra_Pala, accessed
June 27, 2024.
[16] Wikipedia contributors, Vajradhara, 2024. URL: https://en.wikipedia.org/wiki/Vajradhara, accessed
June 27, 2024.
[17] Wikipedia contributors, Supratisthitavarman, 2024. URL: https://en.wikipedia.org/wiki/
Supratisthitavarman, accessed June 27, 2024.
[18] D. Goswami, Garga samhita (english), 2024. URL: https://www.wisdomlib.org/hinduism/book/
garga-samhita-english/d/doc1123336.html, accessed June 27, 2024.
[19] HEURIST, A unique solution to the data management needs of Humanities researchers, https:
//heuristnetwork.org/, 2024. Accessed 25 June 2024.
[20] S. Schiff, S. Melzer, E. Wilden, R. Möller, Tei-based interactive critical editions, in: S. Uchida,
E. Barney, V. Eglin (Eds.), Document Analysis Systems, Springer International Publishing, Cham,
2022, pp. 230–244.
[21] PouchDB Group, Pouchdb, 2024. URL: https://pouchdb.com, [Online; accessed 28-June-2024].
[22] Apache Software Foundation, Apache CouchDB 3 documentation - 2.4. CouchDB replication pro-
tocol, 2024. URL: https://docs.couchdb.org/en/latest/replication/protocol.html, [Online; accessed
28-June-2024].
[23] MDN Web Docs, Using IndexedDB - web APIs, 2024. URL: https://developer.mozilla.org/en-US/
docs/Web/API/IndexedDB_API/Using_IndexedDB, [Online; accessed 28-June-2024].