Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications

A research team introduced an agentic, ontology-guided framework that builds knowledge graphs from scientific literature, and applied it to 2,000 climate science publications to produce a graph with 133,990 nodes and 755,308 relations, with code and data released at github.com/aayushacharya/climatekg. In an agreement study over 1,000 extracted triplets, Gemini-2.5-flash reached Cohen's kappa scores of 0.640–0.700 against three human annotators, within the human–human range of 0.616–0.689, and 98.96% of the 23,327 validated triplets contributed by the publications were judged correct. The framework uses specialized agents for document understanding, information extraction, ontology conformance and entity linking, requiring text-fragment evidence so extracted triples stay semantically consistent and traceable.

arXiv:2610.32725v1 Announce Type: new Abstract: The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts. To address this, we introduce an agentic, ontology-guided framework for knowledge graph KG construction. Our framework utilizes specialized agents for document understanding, information extraction, ontology conformance, and entity linking. First, an LLM extracts factual knowledge in the form of triples with explicit textual evidence from research papers. Then the triplets undergo a multistage verification process to ground the triplets in the ontology. By enforcing schema constraints and requiring evidence in the form of text fragments, we ensure the data is both semantically consistent and traceable. In an agreement study over 1,000 extracted triplets, Gemini-2.5-flash achieves Cohen's $\kappa$ scores of 0.640--0.700 against three human annotators, matching the human--human agreement range of 0.616--0.689. We applied this framework to 2,000 scientific publications and construct a novel, ontology-grounded KG for climate science with 133,990 nodes and 755,308 relations; of the 23,327 triplets that the publications contribute after validation, 98.96\% are judged correct. The pipeline code and KG is publicly available https://github.com/aayushacharya/climatekg.