Tag
This paper studies whether ontology-derived checks reliably validate LLM agents answering questions over knowledge graphs, comparing curated, LLM-generated, and data-derived ontologies and finding that curated ontologies can flag correct answers more often than alternatives, with flags only marginally more precise than random.
sparqlite is a Rust-based SQLite loadable extension that stores RDF quads in ordinary SQLite tables and natively executes SPARQL 1.1 queries, achieving 3.5× speedups over SQL translation while passing 636 of 639 W3C evaluation tests — notably generated by Claude Code's Ultracode agentic workflow over a 12-hour run.
This paper presents data stories as narrative documents combining explanatory text, images, and executable SPARQL queries to enhance accessibility and quality assessment in cultural heritage knowledge graphs, using an AI-supported authoring platform called LODEON.
This paper presents GPTKB 2.0, a large-scale disambiguated knowledge base derived from LLMs, containing 38.4M triples over 1.6M canonical entities. It offers a web interface for browsing, SPARQL/ natural language querying, and auditing fact provenance and disambiguation decisions.
ProbSPARQL is an upward-compatible SPARQL extension that models uncertain numeric values as random variables with probabilistic RDF literal datatypes, enabling distribution-aware queries, probabilistic filters, and divergence-based joins. Implemented on Apache Jena ARQ, it addresses challenges in querying multi-dimensional uncertain measurement data from circular manufacturing knowledge graphs.
Fluree DB is an open-source, temporal graph database with git-like branching, integrated vector/text/geo search, fine-grained access control, and support for SPARQL, JSON-LD, and Open Cypher. It is optimized for AI agent memory and achieves high performance on billion-scale graphs.
DeSQ is a decomposition-based framework for generating SPARQL queries from natural language questions. It breaks complex questions into atomic constraints, maps them to SPARQL fragments, and assembles them into complete queries, outperforming state-of-the-art on four out of five benchmarks.