Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying

Abstract:Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a machine-readable substrate for artificial-intelligence applications. One promising application is translating natural-language questions into SPARQL (text-to-SPARQL), which would let building operators query these graphs through language agents, but progress is limited by the scarcity of large natural-language/SPARQL benchmarks. This paper presents Build2SPARQL, a large-scale benchmark for building KGs generated by a KG-grounded pipeline: SPARQL queries are produced and validated entirely by graph-traversal code, while large language models generate only the natural-language questions, keeping query correctness independent of model behavior. The pipeline mines six query-pattern families -- linear chains, branching, UNION, aggregation, OPTIONAL, and attribute-filtered -- and phrases each query across five vocabulary registers. Applied to 201 building KGs (180 Brick, 21 ASHRAE 223P), it yields 6,136 executable SPARQL queries and 30,680 questions. A two-rater human validation of 300 questions found 98.8% semantic fidelity, 98.8% naturalness, and 84.0% operational plausibility. A retrieval-augmented evaluation across three open-weight language models raised exact-match accuracy from 0.2-20% (zero-shot) to 56-65% (three-shot retrieved).

26 pages, 2 figures, 16 tables. Data paper. Dataset openly available at this https URL. Under review at the ASCE Journal of Computing in Civil Engineering

Artificial Intelligence (cs.AI)

H.2.3; I.2.4; I.2.7

arXiv:2610.00224 [cs.AI]

(or arXiv:2610.00224v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.00224 arXiv-issued DOI via DataCite (pending registration)