Article: Bridging semantic knowledge and generative AI: a modular framework for automated reporting in digital commissioning management Journal: International Journal of Generative Artificial Intelligence in Business (IJGAIB) 2026 Vol.1 No.1/2 pp.36 - 51 Abstract: This paper proposes a framework integrating semantic triple stores with large language models (LLMs) to enhance automated report generation in digital commissioning systems. It addresses the challenge of efficiently extracting and analysing complex industrial data by combining RDF graphs with LLM-based natural language processing. The approach involves: 1) developing an ontology for digital commissioning; 2) structuring data as RDF triples; 3) integrating triplestores with LLMs using LangGraph and LangChain. This enables natural language querying with high semantic accuracy. Using a simulated dataset, the system achieved 100% accuracy in SPARQL query generation across diverse question types, effectively handling entity relationships, hierarchies, and query complexities. The framework bridges structured data and natural language interfaces in industrial contexts, improving efficiency and accuracy in data retrieval and reporting. Future research should explore scalability, heterogeneous datasets, and data quality challenges in real-world implementations. Inderscience Publishers - linking academia, business and industry through research

You can view the full text of this article for free using the link below.

Title: Bridging semantic knowledge and generative AI: a modular framework for automated reporting in digital commissioning management

Authors: Renato Ramos; Diego Calvetti; Daniel Luiz de Mattos Nascimento; Fernando Gussao Bellon

Addresses: CERTI Foundation, UFSC Campus Universitário – Sector C, 88040-970 Florianópolis, P.O. Box 5053, SC, Brazil ' School of Civil Construction, Pontificia Universidad Católica de Chile, Av. Vicuña Mackenna 4860, Macul, Santiago – 7820436, Chile ' Business School, University of Barcelona, Tower 2, Suite 2303, Barcelona – 08034, Spain ' CERTI Foundation, UFSC Campus Universitário – Sector C, 88040-970 Florianópolis, P.O. Box 5053, SC, Brazil

Abstract: This paper proposes a framework integrating semantic triple stores with large language models (LLMs) to enhance automated report generation in digital commissioning systems. It addresses the challenge of efficiently extracting and analysing complex industrial data by combining RDF graphs with LLM-based natural language processing. The approach involves: 1) developing an ontology for digital commissioning; 2) structuring data as RDF triples; 3) integrating triplestores with LLMs using LangGraph and LangChain. This enables natural language querying with high semantic accuracy. Using a simulated dataset, the system achieved 100% accuracy in SPARQL query generation across diverse question types, effectively handling entity relationships, hierarchies, and query complexities. The framework bridges structured data and natural language interfaces in industrial contexts, improving efficiency and accuracy in data retrieval and reporting. Future research should explore scalability, heterogeneous datasets, and data quality challenges in real-world implementations.

Keywords: generative AI; knowledge graphs; digital commissioning; large language models; LLMs; semantic web.

DOI: 10.1504/IJGAIB.2026.151809

International Journal of Generative Artificial Intelligence in Business, 2026 Vol.1 No.1/2, pp.36 - 51

Received: 31 Jul 2025
Accepted: 19 Aug 2025
Published online: 20 Feb 2026 *

Full-text access for editors Full-text access for subscribers Free access Comment on this article

Title: Bridging semantic knowledge and generative AI: a modular framework for automated reporting in digital commissioning management

Keep up-to-date