KBpedia is a recently announced knowledge structure that integrates six major knowledge bases (OpenCyc, Wikipedia, Wikidata, GeoNames, DBpedia, UMBEL) under the KBpedia Knowledge Ontology (KKO). KBpedia's explicit purpose is to provide a foundation for knowledge-based artificial intelligence by supporting the (nearly) automatic creation of training corpuses and positive and negative training sets and feature sets for deep, unsupervised and supervised machine learning. KKO is the upper ontology for KBpedia, and is guided by the universal categories (Firstness, Secondness, Thirdness) of Charles S. Peirce. In this forum, one of KBpedia's co-developers, Mike Bergman, will discuss what KBpedia is, how it is organized and constructed, and why KKO offers some new approaches to vexing metaphysical questions in ontology design related to the knowledge representation of entities, relations, attributes, concepts, and natural kinds. The discussion period will hopefully highlight next potentials and important open questions.
(3D1)
