Since the Message Understanding Conferences on Information Extraction in the 80's and 90's, Named Entity ReCognition (NERC) is a well-established task in the Natural Language Processing (NLP) community. However, very different systems seem to perform very similarly when applied to the same corpus. In this paper, we present a state-of-the-art NERC system. This tool is a hybrid system, based on different resources and techniques. We then propose a protocol to “deconstruct” and evaluate the different components of a complex named entity recognition system. We examine the performance of such a system with learning capacities and reduced initial knowledge on medium-size unlabelled corpora.