In some implementations, text is extracted from a digital work and proper nouns are identified in the text to generate a list of names. The list of names may be sorted so that names containing more information are positioned toward the beginning of the list. The list may be traversed to cluster names and alternate names into name sets that correspond to particular entities in the digital work. Non-unique names that appear in more than one name set may be disambiguated based on proximity to unique names in the same name sets to determine which occurrences of the non-unique names belong with which name sets. Furthermore, a representative name may be selected from among multiple names in a name set for use in representing an entity or object corresponding to the name set. In some examples, the representative name may be selected based on a fullness of the name.