Welcome to DisamKB
A large general-domain knowledge base entirely from a large language model
100 million
triples
6.1 million
entities
10x
less cost

Overview


This interface presents DisamKB v1.5, a large general-domain knowledge base (KB) 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-4.1, DisamKB v1.5 contains 100 million triples for more than 6.1 million entities, at a cost 10x less than previous KBC projects. We also provide DisamKB v1.1 for download.

DisamKB is a landmark for two fields:
  • For NLP, for the first time, it provides constructive insights into the knowledge (or beliefs) of LLMs.
  • For the Semantic Web, it shows novel ways forward for the long-standing challenge of general-domain KB construction.
Using the search field, you can find entities by name, and browse their triples. Alternatively, you can write SPARQL queries or download the whole KB as a TTL file. Paper and code are also available.

Please wait…