In this paper we present the extension of WOLF, a freely available, automatically creat- ed wordnet for French, the biggest drawback of which has until now been the lack of general concepts that are typically expressed with highly polysemous vocabulary that is on the one hand the most valuable for applications in human language technologies but also the most difficult to add to wordnet accurately with automatic methods on the other. Using a set of features, we train a Maximum Entropy classifier on the existing core wordnet to be able to assign appropriate synset ids to new words, extracted from multiple, multilingual sources of lexical knowledge, such as Wik- tionaries, Wikipedias and corpora. Automatic and manual evaluation shows high coverage as well as high quality of the resulting lexico-semantic repository of. Another important ad- vantage of the approach is that it is fully au- tomatic and language-independent and could therefore be applied to any other language still lacking a wordnet.