The goal of entity matching in knowledge graphs is to identify entities that\nrefer to the same real-world objects using some similarity metric. The result\nof entity matching can be seen as a set of entity pairs interpreted as the\nsame-as relation. However, the identified set of pairs may fail to satisfy some\nstructural properties, in particular transitivity, that are expected from the\nsame-as relation. In this work, we show that an ad-hoc enforcement of\ntransitivity, i.e. taking the transitive closure, on the identified set of\nentity pairs may decrease precision dramatically. We therefore propose a\nmethodology that starts with a given similarity measure, generates a set of\nentity pairs that are identified as referring to the same real-world objects,\nand applies the cluster editing algorithm to enforce transitivity without\nadding many spurious links, leading to overall improved performance.\n