Query-directed discovery and alignment of collections of document passages for improving named entity disambiguation precision

A computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable storage devices, and program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

• program instructions to receive a collection of a plurality of discovered entity bins, each of the plurality of discovered entity bins comprising one or more unstructured documents each comprising one or more mentions of a name element from a name query, each of the plurality of discovered entity bins identified with a particular named entity from among a plurality of named entities identifiable from the name element;
• program instructions to identify, from a knowledge base of a plurality of structured documents, for each of one or more identifier components with the name element, a plurality of candidate records identifying the respective one or more identifier components with the name element, the one or more identifier components identified among the plurality of discovery entity bins;
• program instructions to apply, for each respective selection of the plurality of candidate records associated with each of the plurality of discovered entity bins, one or more alignment threshold rules to rank the likelihood that each candidate record within each respective selection matches one or more characteristics of the respective discovery entity bin;
• program instructions to align, with each of the plurality of discovery entity bins, a highest ranked record from among each respective selection of the plurality of candidate records;
• and
• program instructions to output the plurality of discovered entity bins each annotated with the respective aligned highest ranked record identifying a distinct named entity from among the plurality of named entities.

A computer program product comprises a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a computer to cause the computer to:

• receive, by a computer, a collection of a plurality of discovered entity bins, each of the plurality of discovered entity bins comprising one or more unstructured documents each comprising one or more mentions of a name element from a name query, each of the plurality of discovered entity bins identified with a particular named entity from among a plurality of named entities identifiable from the name element;
• identify, by the computer, from a knowledge base of a plurality of structured documents, for each of one or more identifier components with the name element, a plurality of candidate records identifying the respective one or more identifier components with the name element, the one or more identifier components identified among the plurality of discovery entity bins;
• apply, by the computer, for each respective selection of the plurality of candidate records associated with each of the plurality of discovered entity bins, one or more alignment threshold rules to rank the likelihood that each candidate record within each respective selection matches one or more characteristics of the respective discovery entity bin;
• align, by the computer, with each of the plurality of discovery entity bins, a highest ranked record from among each respective selection of the plurality of candidate records;
• and
• output, by the computer, the plurality of discovered entity bins each annotated with the respective aligned highest ranked record identifying a distinct named entity from among the plurality of named entities.