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

arXiv: https://arxiv.org/abs/2609.14652 · HTML: https://mlsanity.com/paper/2609.14652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs](https://mlsanity.com/paper/2312.05934/) (2023)
- [Understanding Catastrophic Forgetting in Language Models via Implicit Inference](https://mlsanity.com/paper/2309.10105/) (2023)
- [SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions](https://mlsanity.com/paper/2407.11417/) (2024)
- [A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases](https://mlsanity.com/paper/2311.07509/) (2023)
- [LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs](https://mlsanity.com/paper/2410.06062/) (2024)
- [OpenCitations, an infrastructure organization for open scholarship](https://mlsanity.com/paper/1906.11964/) (2019)
- [SemOpenAlex: The Scientific Landscape in 26 Billion RDF Triples](https://mlsanity.com/paper/2308.03671/) (2023)
- [FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs](https://mlsanity.com/paper/2508.10467/) (2025)
- [SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions](https://mlsanity.com/paper/2512.14277/) (2025)
- [Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmark](https://mlsanity.com/paper/2603.06582/) (2026)
- [The Case for Text-to-SQL Friendly Logical Database Design](https://mlsanity.com/paper/2606.03145/) (2026)
- [GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons](https://mlsanity.com/paper/2604.21133/) (2026)

## Abstract (arXiv)

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%).