GPTKB

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.

Based 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.