In recent years, the open data (LOD) paradigm has emerged as a promising approach to structuring, publishing, and sharing data online, using Semantic Web standards. From a geospatial perspective, one of the key challenges consists of bridging the gap between the vast amount of crowdsourced, semi-structured or unstructured geo-information and the Semantic Web. Notably, OpenStreetMap (OSM) has gathered billions of objects from its contributors in a spatial folksonomy. The contribution of this paper is twofold. First, we add a piece to the LOD jigsaw, the OSM Semantic Network, structuring it as a W3C Simple Knowledge Organization System (SKOS) vocabulary, and discussing its role in the constellation of geo-knowledge bases. Second, we devise
, a mapping approach between a given vocabulary and WordNet, a pivotal component in the LOD cloud. Our approach is evaluated on the OSM Semantic Network against a human-generated alignment, obtaining high precision and recall.