# What is Knowledge Graph? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Data Infrastructure  
> **Canonical Citation:** [https://spidits.com/ai-glossary/knowledge-graph](https://spidits.com/ai-glossary/knowledge-graph)

## Definition
A Knowledge Graph is a structured database representing a network of real-world entities (nodes) and their semantic relations (edges), allowing systems to query logical context.

## Architectural Mechanics & Deep Dive
A knowledge graph is a structured representation of information that models entities (e.g., people, concepts, objects) as nodes, and their relationships as edges. By organizing data semantically rather than in flat tables, knowledge graphs enable semantic search, multi-hop reasoning, and structured data querying. They are frequently used to ground LLM outputs in corporate domains (Graph RAG).

## Industry Applications & Real-World Use Cases
Search engines, corporate data mapping, and Graph RAG applications.

## Frequently Asked Questions

### What is a triple in a knowledge graph?
The basic unit of data structured as Subject-Predicate-Object (e.g. "Paris" - "capital of" - "France").

### How is a knowledge graph useful in RAG systems?
It helps the retriever map global relationships across disconnected documents, preventing isolated chunk searches.

## Related Terminology
- [graph-rag](https://spidits.com/ai-glossary/graph-rag)
- [vector-database](https://spidits.com/ai-glossary/vector-database)
- [semantic-search](https://spidits.com/ai-glossary/semantic-search)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*