Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window

原文：Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window

作者：Blake G. Fitch

来源：arXiv cs.DB（数据库）

正文

Computer Science > Databases

arXiv:2609.14652v1 (cs)

[Submitted on 13 Sep 2026]

Title:Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window

Authors:Blake G. Fitch

View a PDF of the paper titled Natural Language Knowledge Graph Query Execution: Leveraging Controlled Semantics in the LLM Context Window, by Blake G. Fitch

View PDF

HTML (experimental)

Abstract:Large Language Model (LLM) applications often transfer domain concepts into the model’s context informally, through prompt prose, schema dumps, and examples. We show that for database queries, data model concepts pass to LLMs more effectively through representations whose vocabulary terms carry declared, machine-readable semantics (controlled semantics). NLKGQ is a working system and reusable framework that does this for data modeled in a knowledge graph. A formal OWL ontology serves as the transfer mechanism, concentrating the meaning of the data into semantically precise tokens the model can use directly. In a single LLM call, NLKGQ places in the context a system prompt instructing on SPARQL, the complete domain OWL ontology, and a domain-specific prompt addition, together with the user’s natural language query. The model then generates the SPARQL query directly, zero-shot. Where the native vocabulary of an existing database or federation of databases is opaque, a wrapper ontology substitutes clean terms and a runtime rewriter restores the native forms. Evaluating on DBLP-QuAD 2.0 showed that its scores depend on the graph snapshot, the endpoint used, and the wording of its machine-generated questions, so we propose DBLP-QuAD 3.1, which maintains the intent of 2.0 while making reference results deterministic, revising reference SPARQL where needed, and rewriting the natural language questions, with a frontier model, to state each reference query’s intent clearly and completely. We evaluate on the DBLP-QuAD 2.0 benchmark (57.6% Match under deterministic re-scoring), DBLP-QuAD 3.1 (89.9% Match on 1,000 questions), SemOpenAlex (98% Match against a published baseline’s 86% on the identical test set), and neuroimaging metadata (100%).

Comments:

9 pages, 4 tables

Subjects:

Databases (cs.DB); Artificial Intelligence (cs.AI)

Cite as:

arXiv:2609.14652 [cs.DB]

(or

arXiv:2609.14652v1 [cs.DB] for this version)

https://doi.org/10.48550/arXiv.2609.14652

Focus to learn more

arXiv-issued DOI via DataCite

主题

数据库 · 人工智能

由「前沿雷达」于 2026-09-20 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。