This demo extracts entities such as "Apple Inc" and facts about them ("Apple Inc"; founded by; "Steve Jobs") from natural language text.
The result is a knowledge graph containing facts described in the text (blue edges) as well as facts from the Diffbot Knowledge Graph (gray edges).
The Diffbot Knowledge Graph is the world's largest repository of web data with over 10 billion entities and 1 trillion facts.
To pull more facts about an entity from the Diffbot Knowledge Graph, you can double click the circle representing this entity in the tab "Graph".
- Entity. Anything in the real world. Example: Apple Inc, Steve Jobs.
- Entity Type. A class of an entity. Example: organization, person.
- Fact. A fact defines a relationship between entities (Apple Inc; founded by; Steve Jobs) or an entity and a literal (Apple Inc; number of employees; 137,000).
- Property. A property defines the relationship type (founder, number of employees) of a fact.
- Open Fact. Unlike a regular fact, an open fact does not follow a pre-defined list of properties. An open fact's property is extracted directly from the text. This enables new properties to be discovered.
- Sentiment of a document. This value represents the overall sentiment of the text. It ranges from -1.0 (very negative) to 1.0 (very positive). Sentiment around 0.0 is considered neutral.
- Sentiment of an entity. This value represents the sentiment of the text towards an entity. Example: "I love Apple products, but the new iMac Pro is too pricey." is positive towards Apple and negative towards the Mac Pro.
- Salience. This value helps answer the question: "What is this text mainly about?". Salience of 1.0 means the entity is the main topic of the document, while salience of 0.0 means that the entity is unnecessary to understand the document.