This research introduces a multi-step pipeline for automatically structuring complex knowledge from large document collections in highly specialized fields.

• Constructs the first comprehensive knowledge graph for nuclear fusion energy
• Employs automatic named entity recognition and entity resolution techniques
• Demonstrates effective information elicitation and retrieval from complex technical documents
• Provides a framework that can be applied to other specialized domains

This engineering innovation creates an organized, accessible knowledge structure for a field critical to future energy solutions, helping researchers navigate vast technical information more effectively.

Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information