Definition
What is a Knowledge Graph? — Plain-Language AI Definition
A structured network of real-world entities and their relationships — like a web of connected facts that AI can navigate to find accurate information and make logical connections.
What is a Knowledge Graph?
A knowledge graph is a structured database that represents real-world entities (people, places, concepts, products) and the relationships between them as a network of interconnected nodes. Think of it as a web of facts where every piece of information is connected to related pieces.
How It Works (Simplified)
Imagine a network where:
- Nodes represent things (people, companies, concepts)
- Edges represent relationships between them
Example:
- "Albert Einstein" → [worked at] → "Princeton University"
- "Albert Einstein" → [born in] → "Ulm, Germany"
- "Albert Einstein" → [developed] → "Theory of Relativity"
- "Theory of Relativity" → [is a] → "Physics Theory"
This structure lets you traverse relationships: "Who else worked at Princeton?" or "What other physics theories exist?"
Real-World Knowledge Graphs
| Knowledge Graph | Creator | Used For |
|---|---|---|
| Google Knowledge Graph | Powers Google Search info boxes | |
| Wikidata | Wikimedia | Open knowledge base with 100M+ items |
| Microsoft Academic Graph | Microsoft | Academic paper relationships |
| Amazon Product Graph | Amazon | Product relationships and recommendations |
| Enterprise KGs | Various | Internal company knowledge management |
Knowledge Graphs + AI
Knowledge graphs and LLMs complement each other:
| Capability | LLM Alone | LLM + Knowledge Graph |
|---|---|---|
| Factual accuracy | May hallucinate | Grounded in verified facts |
| Explainability | "Black box" reasoning | Can show the reasoning path |
| Currency | Frozen at training date | Updated in real time |
| Structured queries | Struggles with precision | Precise relationship traversal |
Professional Use Cases
- Healthcare: Map relationships between diseases, symptoms, treatments, and drug interactions
- Legal: Connect cases, statutes, judges, and legal concepts for research
- Finance: Map company relationships, ownership structures, and market connections
- Sales/CRM: Map relationships between contacts, companies, deals, and products
- Research: Navigate academic citation networks and discover related work
Knowledge Graph vs. Vector Database
| Dimension | Knowledge Graph | Vector Database |
|---|---|---|
| Data type | Structured entities and relationships | Unstructured text embeddings |
| Query type | "What is X related to?" | "Find text similar to this" |
| Strength | Precise, explainable relationships | Fuzzy semantic similarity |
| Best for | Navigating known structures | Finding relevant unstructured content |
Key Takeaway
Knowledge graphs bring structure and precision to AI systems. They are especially valuable when you need factual accuracy, explainability, and the ability to navigate complex relationships — qualities that LLMs alone sometimes lack.
Related Terms
Learn This in Practice
Move from definition to application with guides and resources that show how this concept appears in real AI workflows.
Get AI Tips Every Week
Get smarter about AI every week — practical tips, prompts, and workflows in your inbox.