Systems and methods are provided for generating a places dataset comprising place data from multiple data sources each having a plurality of place data. Based on the places dataset, the systems and methods generate local clusters comprising places located within a predetermined distance, generate probable pairs of places in each local cluster, and distribute the probable pairs to one or more processors to determine similar edges between one or more places in each local cluster based on a plurality of combined similarity measures indicating whether or not a place is similar to another place. The systems and methods further generate similar pairs based on the combined similarity measures and convert the similar pairs into connected components comprising groups of similar places based on a best similar edge from all the candidates for a group of similar places.