Part III: Building knowledge graphs from text

The transformation of unstructured textual data into structured, actionable knowledge represents one of the most exciting frontiers in the development of intelligent systems. This part explores the powerful combination of Knowledge Graphs and Large Language Models in extracting, structuring, and representing knowledge from text, demonstrating how these technologies complement each other to unlock value from the vast amounts of unstructured information that organizations possess.

While Part II focused on building knowledge graphs from structured data sources, this part tackles the more challenging realm of unstructured text—which comprises 80-90% of enterprise data today. The integration of LLMs has revolutionized this domain, bringing unprecedented capabilities in understanding and extracting meaningful information from natural language and reducing the necessity of human labor. However, the true power emerges when these capabilities are combined with traditional NLP techniques and knowledge graph technologies, creating systems that can both understand context and maintain structured, verifiable knowledge representations.

The chapters in this part guide readers through the complete lifecycle of text-to-knowledge-graph conversion, from initial entity extraction to sophisticated disambiguation and relationship mapping. Through real-world case studies and practical implementations, they demonstrate how to: