The Name Finder can detect named entities and numbers in text. It is currently set to detect persons (proper names), organizations, locations, times, dates, money, and percentages. To be able to detect entities the Name Finder needs a model. The model is dependent on the language and entity type it was trained for. The OpenNLP projects offers a number of pre-trained name finder models which are trained on various freely available corpora. They are available in data://ApacheOpenNLP/models/. To find names in raw text the text must be segmented into tokens and sentences, which this implementation handles by default for standard English. Its important that the tokenization for the training data and the input text is identical, so if working with something other than standard English, you need to pick different models from the models directory or train your own.
For more information visit http://opennlp.apache.org.