GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge

Authors

  • Yujia Hu ScaDS.AI Dresden/Leipzig & TU Dresden, Germany
  • Tuan-Phong Nguyen VNU University of Engineering and Technology, Hanoi, Vietnam
  • Shrestha Ghosh University of Tübingen, Germany
  • Moritz Müller ScaDS.AI Dresden/Leipzig & TU Dresden, Germany
  • Simon Razniewski ScaDS.AI Dresden/Leipzig & TU Dresden, Germany

DOI:

https://doi.org/10.1609/aaai.v40i48.42354

Abstract

Language models are powerful artifacts, yet their factual knowledge is still poorly understood, and inaccessible to ad-hoc browsing and scalable statistical analysis. This demonstration introduces GPTKB v1.5, a densely interlinked 100-million-triple knowledge base (KB) built for $14,000 from GPT-4.1, using the GPTKB methodology for massive-recursive LLM knowledge materialization. This demo focuses on three use cases: (1) link-traversal-based LLM knowledge exploration, (2) SPARQL-based structured LLM knowledge querying, (3) comparative exploration of the strengths and weaknesses of LLM knowledge. Massive-recursive LLM knowledge materialization is a groundbreaking opportunity both for the systematic analysis of LLM knowledge, as well as for automated KB construction.
AAAI-26 / IAAI-26 / EAAI-26 Proceedings Cover

Downloads

Published

2026-03-14

How to Cite

Hu, Y., Nguyen, T.-P., Ghosh, S., Müller, M., & Razniewski, S. (2026). GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41604–41606. https://doi.org/10.1609/aaai.v40i48.42354

Issue

Vol. 40 No. 48: EAAI-26 AI for Education, Model AI Assignments, AAAI-26 Emerging Trends, Doctoral Consortium, Student Abstracts, Undergraduate Consortium and Demonstrations

Section

AAAI Demonstration Track