StanfordNLP / DeterministicCoreferenceResolution / 0.1.1
This is built from the Stanford Deterministic Coreference Resolution System ( It takes text (as a String) as input and outputs a list of maps, in which each map contains the name of an entity (specifically, its most representative mention) as key and a list of other mentions of that entity as values. For instance, in the text "Bob visited the university. He then enrolled." yields input [{"Bob":["He"]}], meaning the "Bob" is the most representative mention of the person Bob, and the later word "He" refers to the same entity.

For more information, please refer to or Manning, Christopher D., Surdeanu, Mihai, Bauer, John, Finkel, Jenny, Bethard, Steven J., and McClosky, David. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55-60.