Traditional Entity Linking is the task of linking name mentions in Web text with their referent entities in a knowledge base, and thus plays an important role in a range of Internet services, such as online recommender systems and Web search Engines. However, in our data integration framework, entity linking becomes the performance bottleneck. The reason is that data records of data integration systems are often short, noisy, informal texts with little context, and often contain phrases with ambiguous meanings. To rigorously address the entity linking problem for data integration, a novel graph-based short text entity linking framework is proposed. Firstly a hybrid candidate entity selection approach that considers both text description and instance data is introduced, then a graph-based semantic similarity metric combining context, topic and semantic correlation for short text entity disambiguation is proposed. Experimental results show good precision and recall of the proposed approaches.