Knowledge Graphs can contain millions of entities. Entities (like persons, animals or films) have identifiers. Use the button below to get some examples out of 179,706,494 available entities.
Embeddings can be computed through analysis of properties and relationships of entities. Embeddings are vectors with the desired property that close embeddings correspond to a semantic similarity of related entities. Use the form below to view an example.
The current version of this website serves data for a scientific conference review of the article Universal Knowledge Graph Embeddings. We removed some parts, e.g. contact information. These parts will be re-added after the review process.
The Universal Embeddings are based on embeddings computed on data from DBpedia and Wikidata with ConEx.
You can find the underlying data dump at Zenodo.
We also offer embeddings as a service with a convenient API.