GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base

• URL: http://arxiv.org/abs/2608.06992v1
• Date: Fri, 07 Aug 2026 09:10:30 GMT
• Title: GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base
• Abstract summary: We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM)<n>GPTKB 2.0 contains 38.4M triples over 1.6M canonical entities, together with 207.6K consolidated relations and 66K consolidated classes.<n>The interface further supports structured SPARQL queries, natural-language questions translated to SPARQL, and entity linking from user-provided text to canonical GPTKB 2.0 entries.
• Score: 11.119171720690238
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM). GPTKB 2.0 contains 38.4M triples over 1.6M canonical entities, together with 207.6K consolidated relations and 66K consolidated classes. Unlike prior LLM-derived knowledge bases that largely identify entities by surface strings, GPTKB 2.0 performs context-guided disambiguation during recursive KB construction, separating homonyms and merging synonymous mentions as facts are elicited. The demo makes this process inspectable: users can browse entities, follow links across the KB, and audit the provenance of individual facts, including surface forms, candidate matches, source triples, and disambiguation decisions. The interface further supports structured SPARQL queries, natural-language questions translated to SPARQL, and entity linking from user-provided text to canonical GPTKB 2.0 entries. GPTKB 2.0 is available at https://gptkb.org/, with the full KB downloadable for offline use.

Related papers

• Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window [0.0]
  We show that for database queries, data model concepts pass to LLMs more effectively through representations whose vocabulary terms carry declared, machine-readable semantics.<n> NLKGQ is a working system and reusable framework that does this for data modeled in a knowledge graph.<n>We evaluate on the DBLP-QuAD 2.0 benchmark (57.6% Match under deterministic re-scoring), DBLP-QuAD 3.1 (89.9% Match on 1,000 questions), SemOpenAlex (98% Match against a published baseline's 86% on the identical test set)
  arXiv  Detail & Related papers  (2026-09-13T16:36:40Z)
• GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models [11.119171720690238]
  GPTKB 2.0 is a methodology for constructing disambiguated KBs directly from large language models.<n>We execute GPTKB 2.0 at scale, obtaining a materialized KB containing over 1M disambiguated entities and 38.4M triples.
  arXiv  Detail & Related papers  (2026-08-04T14:25:47Z)
• Text-to-SPARQL Goes Beyond English: Multilingual Question Answering Over Knowledge Graphs through Human-Inspired Reasoning [51.203811759364925]
  mKGQAgent breaks down the task of converting natural language questions into SPARQL queries into modular, interpretable subtasks.<n> Evaluated on the DBpedia- and Corporate-based KGQA benchmarks within the Text2SPARQL challenge 2025, our approach took first place among the other participants.
  arXiv  Detail & Related papers  (2025-07-22T19:23:03Z)
• Extending dependencies to the taggedPBC: Word order in transitive clauses [0.0]
  This paper reports on a CoNLLU-formatted version of the dataset which transfers dependency information along with POS tags to all languages in the taggedPBC.<n>The dependency-annotated corpora are also made available for research and collaboration via GitHub.
  arXiv  Detail & Related papers  (2025-06-07T12:52:45Z)
• Focus, Merge, Rank: Improved Question Answering Based on Semi-structured Knowledge Bases [2.6524539020042663]
  We present FocusedRetriever, a modular SKB-based framework for multi-hop question answering.<n>It integrates components (VSS-based entity search, LLM-based generation of Cypher queries and pairwise re-ranking) in a way that enables it to outperform state-of-the-art methods.<n>The average first-hit rate exceeds that of the second-best method by 25.7%.
  arXiv  Detail & Related papers  (2025-05-14T09:35:56Z)
• Enabling LLM Knowledge Analysis via Extensive Materialization [15.276041443299905]
  We build GPTKB, a knowledge base comprising 101 million triples for over 2.9 million entities GPT-4o-mini.<n>We use GPTKB to internalizedily analyze GPT-4o-mini's factual knowledge in terms of scale, accuracy, bias, and consistency.
  arXiv  Detail & Related papers  (2024-11-07T17:57:03Z)
• SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions [6.933892616704001]
  We introduce the SPINACH dataset, an expert-annotated KBQA dataset collected from discussions on Wikidata's "Request a Query" forum. The complexity of these in-the-wild queries calls for a KBQA system that can dynamically explore large and often incomplete schemas and reason about them. We also introduce an in-context learning KBQA agent, also called SPINACH, that mimics how a human expert would write SPARQLs to handle challenging questions.
  arXiv  Detail & Related papers  (2024-07-16T06:18:21Z)
• Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension [61.079852289005025]
  Cross-lingual question answering over knowledge base (xKBQA) aims to answer questions in languages different from that of the provided knowledge base. One of the major challenges facing xKBQA is the high cost of data annotation. We propose a novel approach for xKBQA in a reading comprehension paradigm.
  arXiv  Detail & Related papers  (2023-02-26T05:52:52Z)
• SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases [57.89642289610301]
  We present SYGMA, a modular approach facilitating general-izability across multiple knowledge bases and multiple rea-soning types. We demonstrate effectiveness of our system by evaluating on datasets belonging to two distinct knowledge bases,DBpedia and Wikidata.
  arXiv  Detail & Related papers  (2021-09-28T01:57:56Z)
• MobIE: A German Dataset for Named Entity Recognition, Entity Linking and Relation Extraction in the Mobility Domain [76.21775236904185]
  dataset consists of 3,232 social media texts and traffic reports with 91K tokens, and contains 20.5K annotated entities. A subset of the dataset is human-annotated with seven mobility-related, n-ary relation types. To the best of our knowledge, this is the first German-language dataset that combines annotations for NER, EL and RE.
  arXiv  Detail & Related papers  (2021-08-16T08:21:50Z)
• Reasoning Over Virtual Knowledge Bases With Open Predicate Relations [85.19305347984515]
  We present the Open Predicate Query Language (OPQL) OPQL is a method for constructing a virtual Knowledge Base (VKB) trained entirely from text. We demonstrate that OPQL outperforms prior VKB methods on two different KB reasoning tasks.
  arXiv  Detail & Related papers  (2021-02-14T01:29:54Z)
• Differentiable Reasoning over a Virtual Knowledge Base [156.94984221342716]
  We consider the task of answering complex multi-hop questions using a corpus as a virtual knowledge base (KB) In particular, we describe a neural module, DrKIT, that traverses textual data like a KB, softly following paths of relations between mentions of entities in the corpus. DrKIT is very efficient, processing 10-100x more queries per second than existing multi-hop systems.
  arXiv  Detail & Related papers  (2020-02-25T03:13:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.