GPTKB 2.0 constructs a 38.4-million-triple knowledge base directly from an LLM, resolving duplicate and ambiguous names at scale without external identifiers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models
GPTKB 2.0 constructs a 38.4-million-triple knowledge base directly from an LLM, resolving duplicate and ambiguous names at scale without external identifiers.