Wikification (entity annotation) is a challenging task in Natural Language Processing (NLP). It is a method to automatically enrich a text with links to Wikipedia as a knowledge base. Wikification starts from detecting ambiguous mentions in the document, and later tries to disambiguate those mentions. In the core of the Wikification task, there is one other important NLP task: word representation. This paper proposes a new word representation for senses of a mention with Graph convolutional networks architecture. Senses are the possible meanings of one mention, based on the knowledge base. In our representation modeling, we used the context document and the first paragraph of each Wikipedia page to enhance our contextual representation. Using the nearest neighbor algorithm for disambiguating the mentions via our sense representations, we show the efficiency of our representations. The results of comparing our method with recent state-of-the-art methods show the efficiency of our solution.