The growing awareness of the importance of spatial information has led to a continuously increasing demand for geospatial data. Thus, a lot of different companies and institutions have evolved that are aiming at satisfying this demand by capturing the real world according to the needs of different applications. This process involves that one and the same real world object is stored in several representations in different geospatial databases. The integration of these representations is a major research challenge in the field of GIS. In our approach we use a semi-automatic matching tool for defining relations between representations on the instance level. These relations are used in order to automatically derive an integrated data schema. The relations on the instance level as well as the integrated data schema can be used for automatically merging data sets, for automatically transferring updates from one data set into another or for a common analysis of spatial data from different sources.