"https://drive.google.com/file/d/1oF6pLrXoVYKh_GRpyC-E4hmFRnzdOF9a/view?usp=share_link

Qualification processes in industrial settings require accurate, equipment-specific inspection criteria from technical documentation to ensure deliverable quality and minimize post-launch downtime and claims. This presents a challenging science problem: how to extract and generate reliable inspection recommendations from heterogeneous data sources, without hallucinations. We developed a hybrid Knowledge Graph-LLM solution that addresses fundamental limitations of LLM-only approaches. Initial approaches exhibited significant hallucinations, generating unreliable inspection values that couldn't be validated against domain constraints, prompting our hybrid solution. Our methodology employs a domain-specific KG that captures semantic relationships between equipment types, failures and inspection requirements. This KG extracts and links entities from diverse historical data sources, including failures and unstructured technical documentation, creating a semantic network for constrained generation. By using graph patterns to constrain LLM inputs, we transformed the task from open generation to structured information insertion, significantly reducing hallucinations. Results demonstrate substantial improvement in inspection recommendation accuracy and consistency, while maintaining extraction efficiency. The methodology offers generalizable findings for bridging structured and unstructured data in domains requiring high-precision AI outputs."