This research enhanced people search engine, EntityCube, returning the object-level information for the matching person, such as bio and related news article, by mapping each name into matching twitter accounts. This mapping would enable users, while browsing the news, can easily connect to social entities (Twitter or Facebook accounts) to get more personal and up-to-date information or even engage a conversation. Existing tools for this purpose build upon naive textual matching and inevitably suffer from low precision, due to false positives (e.g., fake impersonator accounts) and false negatives (e.g., accounts using nicknames). To overcome these limitations, we leverage "relational" evidences extracted from the Web corpus. In particular, as such an example, we adopt Web document co-occurrences, which can be interpreted as an "implicit" counterpart of Twitter follower relationships. Using both textual and relational features, we learn a ranking function aggregating these features for the accurate ordering of candidate matches. This project fully achieved its milestones with publications at top-tier conferences, including EDBT and VLDB.