{"url":"/dataset/gptkb","name":"GPTKB","full_name":null,"description_markdown":"GPTKB is a large general-domain knowledge base (KB) constructed entirely from a large language model (LLM). It demonstrates the feasibility of large-scale KB construction from LLMs, while highlighting specific challenges arising around entity recognition, entity and property canonicalization, and taxonomy construction.\r\n\r\nBased on GPT-4o-mini, GPTKB contains 105 million triples for more than 2.9 million entities, at a cost 100x less than previous KBC projects.","description_withheld":null,"homepage":"https://gptkb.org","introduced_date":"2024-11-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/gptkb-building-very-large-knowledge-bases","title":"Enabling LLM Knowledge Analysis via Extensive Materialization","first_author":"Yujia Hu","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GPTKB"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}