The aim of conflict resolution in data integration systems is to identify the true values from among different and conflicting claims about a single entity provided by different data sources. Most data fusion methods for resolving conflicts between entities are based on two estimated parameters: the truthfulness of data and the trustworthiness of sources. The relations between entities are however an additional source of information that can be used in conflict resolution. In this article, we seek to bridge the gap between two important broad areas, relation estimation and truth discovery, and to demonstrate that there is a natural synergistic relationship between machine learning and data fusion. Specifically, we use relational machine learning methods to estimate the relations between entities, and then use these relations to estimate the true value using some fusion functions. An evaluation of the results shows that our proposed approach outperforms existing conflict resolution techniques, especially where there are few reliable sources.