DBpedia
a Large, Multilingual, Semantic Knowledge Graph
Almost every major Web company has now announced its work on a Knowledge Graph: Google’s Knowledge Graph, Yahoo!’s Web of Objects, Microsoft's Satori Graph, Walmart Lab’s Social Genome, and Facebook’s Entity Graph, just to cite the biggest ones.
DBpedia
DBpedia is a community-run project that has been working on a free, open-source Knowledge Graph since 2006!
DBpedia currently describes 38.3 million “things” of 685 different “types” in 128 languages, with over 4 billion “facts”. It is interlinked to many other datasets. The knowledge in DBpedia is exposed through a technology stack called Linked Data, which has been revolutionizing the way applications interact with the Web: with Linked Data technologies, all APIs are interconnected via standard Web protocols and languages.
The Web of data
Such Web of data provides useful knowledge that can complement the Web of documents in many ways. See, for instance, how bloggers tag their posts or assign them to categories in order to organize and interconnect their blog posts. This is a very simple way to connect unstructured text to a structure (hierarchy of tags). For more advanced examples, see how BBC has created the World Cup 2010 website by interconnecting textual content and facts from their knowledge base.
Or, more recently, did you see that IBM's Watson used DBpedia data to win the Jeopardy challenge?
DBpedia Spotlight
DBpedia Spotlight is an open source text annotation tool that connects text to Linked Data by marking names of things in text (we call that spotting) and selecting between multiple interpretations of these names (we call that disambiguation). For example, Washington can be interpreted in more than 50 ways including a state, a government or a person. You can already imagine that this is not a trivial task, especially when we're talking about millions of things and hundreds of types.
