What is a Knowledge Graph?
An introduction to the concept of a knowledge graph.
A Network of Knowledge
A Knowledge Graph, also known as a semantic network, represents a network of real-world entities—such as objects, events, situations or concepts—and illustrates the relationship between them. This information is usually stored in a graph database and visualized as a graph structure, prompting the term knowledge “graph.”
Think of it as a model of a specific domain, containing all the key objects, facts, and the relationships between them. It is a flexible and intuitive way to represent knowledge that mirrors how we often think about the world—as a network of connected things.
The Core Components
A knowledge graph is made up of three main components:
- Nodes: Any object, place, or person can be a node.
- Edges: An edge defines the relationship between the nodes.
- Labels: A label gives a description of the node or the edge.
For example, a node could be a client, like IBM, and an agency, like Ogilvy. An edge would categorize the relationship as a "customer" relationship between IBM and Ogilvy.
Subject-Predicate-Object
You can think of these relationships as a simple sentence structure: A (the subject) is connected to C (the object) by B (the predicate).
How it Works
Knowledge graphs are typically made up of datasets from various sources, which frequently differ in structure. Schemas, identities and context work together to provide structure to diverse data.
- Schemas provide the framework for the knowledge graph.
- Identities classify the underlying nodes appropriately.
- Context determines the setting in which that knowledge exists.
These components help distinguish words with multiple meanings. This allows products, like Google’s search engine algorithm, to determine the difference between Apple, the brand, and apple, the fruit.
The Knowledge Graph in the Perseus Client
In the context of the Perseus Client, the Knowledge Graph is the primary output of the Text-to-Graph pipeline. It is the structured, interconnected representation of the information extracted from your source files. This graph is now ready for use in your AI applications.
Crucially, the Knowledge Graph object and its constituent sub-objects (Entities, Relations, and Literal Values) are all parsed from the TTL (Terse RDF Triple Language) output provided by the Perseus API once a processing job is successfully completed. This standardized format ensures interoperability and a robust representation of the extracted knowledge.