In this article, we explore an innovative approach to reconstruct the genealogy of the royal family Pal.ola S.a¯hi 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 Pa l.ola S.a¯hi 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.a¯hi 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.
The Gilgit bronze inscriptions, which refer to the Pal.ola S. a¯his royal family, provide valuable insights
into Buddhist culture and patronage in the Gilgit region during the 6th to 8th centuries. [
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 dificult 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 interdisciplinary 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 diferent 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 eforts 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 [
Our research question can be formulated as follows: How can we efectively integrate a LLM ( Large Language Model) with diverse database contents to reconstruct and enrich the genealogy of a family, using the royal Pa.lola S.a¯hi dynasty as a case study? 2. Genealogy of the Pal.ola S. a¯hi 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.a¯hi.
In the article [
We can regard this information from article [
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 diferent language models and tried to obtain further information about the royal family tree: Perplexity.ai1, Ś¯IL A¯DITYANANDIN SOMANA
[Su-fu-she-li-chi-li-ni = Nandivikrama¯dityanandin? *SURENDR A¯DITYA
3. (Maha¯)Dev¯ı Surendra(ma¯la¯) Bhat.t.a¯rika¯ 4. (Maha¯)Dev¯ı Di+ysa¯pu n.ya¯ 5. uvakh¯ı Śr¯ı Maha¯dev¯ı Dilditapu n.ya¯ [6. Jayaprabhat.a¯] 1. Śa¯m¯ıdev¯ı Trailokyadev¯ı Bhat.t.a¯rika¯ 2. Śr¯ı Śa¯midev¯ı Saran. ama¯la¯ 3. Śr¯ı Maha¯dev¯ı Sala¯ n.ahansika¯ [4. Śr¯ı Maha¯dev¯ı Jayaprabhat.a¯] (possibly) 1. Śr¯ımad Ana ṅgadev¯ı 2. Ra¯jñ¯ı Ra¯mama¯la¯ (?) 1. Śa¯madev¯ı Śa¯ma¯vat¯ı 2. Maha¯dev¯ı Ma ṅgalakesar¯ı Śr¯ı Śa¯m¯ıdev¯ı Namobuddha¯ya ca. 532 AD 6th century 585 - 605 AD 605 - 625 AD 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 Pa l.ola S. a¯hi 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. 2https://uhhgpt.uni-hamburg.de/ 3https://chatgpt.com/ 4https://gpt4all.io/ Deva Shahi Navasurendra¯ditya Nandi Vajradhara Indra Pala
Sri Deva Palola Shahi
Mid-7th century CE
Early 8th century CE
Late 8th century CE
Early 9th century CE
Comment: ChatGPT’s answer presumably has other names of the kings. In [
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 Ra¯jad. i Teja d.i, who was a noble lady and possibly also the sister of Ra¯jad. i. Another member of the ruling family was bha¯rya¯ J¯ıjad. i, whose name means “daughter of J¯ıja¯.” [. . .] 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 genealogy defined by Luo Wenhua and Oskar von Hinüber. The diferences are as follows. First, King Ś¯ILA¯ DITYANANDIN (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 (Sa m.)Pu¯r n.adityanandin of King SURENDR(AVIKRAM)A¯ DITYANANDIN is not mentioned in Table 3. It is not clear whether or not he ever ruled. Third, the reign time of the last King SURENDR A¯DITYA is given as 720-740 or 750 CE, Somana Vajraditayanandin Vikramadityanandin Surendravikramadityanandin Navasurendra¯ditya-nandin Jayama ṅgalavikrama¯ditya-nandin Nandivikramadityanandin Su-fu-che-li-chi-li-ni Surendradityanandin Mid-6th century CE 585-605 CE 605-625 CE 625-644 or 654 CE 644 or 654-685 CE 685-710 CE 710-715 CE 715-720 CE 720-740 or 750 CE 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 Tegin.
ChatGPT delivers an overview about kings from another dynasty, e. g. Shahi Answer 2: GPT4All with Mistral Instruct [. . .] The genealogy of the royal family Palola Shahi can be traced back to Ra¯jad. i Tejad. i, who was a noble lady and perhaps also a member of the ruling family. She had two daughters: Sara and bha¯rya¯ J¯ıja d.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 Ra¯jad. i Teja d.i II and bha¯rya¯ J¯ıja d.i II. The dynasty continued to rule for several centuries, with notable rulers such as Man. galavikrama¯dityanandi and Ra¯ja¯ d.i Teja d.i III. [. . .]
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 Navasurendra¯ditya-nandin
Kuma¯ra¯ja Jayavarman Lalita¯ditya Father
Navasurendra¯ditya-nandin
Kuma¯ra¯ja Jayavarman Son
Kuma¯ra¯ja Jayavarman Lalita¯ditya 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 Na¯masi m.ha (1250-1300), who is considered as the first king of the Palola Shahi. He had four queens: Di + (ysa)pun. ya¯, Ra¯jñ¯ı Tejad. i, Ra¯jad. i, and Bha¯rya¯ J¯ıja d.i. Na¯masi m.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 → Devaśa¯ntika; queens → Śr¯ı Prabha¯vat¯ı (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: Śr¯ı Prabha¯vat¯ı: children with Somana → Somila (son and successor); son → Somila; father → Somana; mother→ Śr¯ı Prabha¯vat¯ı Comment: In contrast to Luo Wenhua’s and Oskar von Hinüber’s researches, there’s no information about King Somana’s queens. The name Śr¯ı Prabha¯vat¯ı 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.
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 VAJRA¯ DITYANANDIN 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 Vajra¯dityanandin: father → Navasurendra¯ditya-nandin; son → Nandivikrama¯dityanandin (likely successor) • Father: Navasurendra¯ditya-nandin: father → Supratis.t.hitavarman; children → Vajra¯dityanandin (son, and eventual king); possibly other children, but not clearly mentioned in available records. • Son: Nandivikrama¯dityanandin; father → Vajra¯dityanandin Comment: ChatGPT’s answer is not correct. The King Vajra¯dityanandin could not be the son of Navasurendra¯ditya-nandin because Navasurendra¯ditya-nandin ruled later (cf. Table 1). The son’s name of the king Navasurendradityanandi was Jayama ṅgalavikrama¯dityanandi (cf. Table 1). Answer 6: GPT4All using Mistral Instruct The genealogy of King Vajra¯dityanandin of the Royal Family Palola Shahi is as follows: • Father: Maharaja Na¯masi m.ha (1) • Mother: Queen Di + (ysa)pu n.ya¯ (2) • Sons: Prince Ra¯jñ¯ı Teja d.i (3), Prince Sara (4) • Daughters: Princess Bha¯rya¯ J¯ıja d.i (5) [. . .]
Comment: GPT4all delivers the name Di + (ysa)pun. ya¯ as the mother of the king Vajra¯dityanandin, but she was the 4th queen of the king Vikramadityanandin, the successor of Vajra¯dityanandin. The other results could not be confirmed. This information can not be found in Vol. XX (2017) (page 136, 140).
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
efectiveness with large datasets may be limited [
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. PouchDB PouchDB [21] is a powerful and versatile open-source JavaScript database that ofers 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 ofline, storing data locally in the browser’s Web storage, such as IndexedDB [23] in Firefox. This “Ofline 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 ofers several advantages over the simpler table structure shown in Figure 2.
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 diferent agents with (diferent 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
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 [
At the start, we first tried to obtain information about the entire repository, i.e. the genealogy of the Pal.ola S. a¯hi 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. a¯hi, whereby no new ifndings could be provided by the agents in our research.
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 [
In this article, we present an innovative approach to reconstruct the genealogy of the royal family Pal.ola S. a¯hi 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.a¯hi 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. a¯hi family using traditional methods, without any new findings from the used agents.
The research for this contribution was funded by the Deutsche Forschungsgemeinschaft (DFG, German 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. [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. Schif, 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 protocol, 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].