Machine learned historically accurate temporal classification of objects

A computer program product comprising:

• a computer readable storage medium readable by one or more processors and storing instructions for execution by the one or more processors for performing a method comprising:
• ingesting, by the one or more processors, content from one or more sources of content and, for each source of the one or more sources of the content, one or more attributes comprising a verified temporal context of the source, wherein the verified temporal context attribute comprises an assurance that content associated with the verified temporal context attribute is consistent with date and time data associated with the content, wherein the assurance is based on an image in the content being consistent with the date and time data associated with the content;
• cognitively analyzing, by the one or more processors, the content, by applying one or more entity recognition algorithm, to the content, to identify and extract entities in each source;
• classifying, by the one or more processors, each extracted entity of the extracted entities in a given grouping of a plurality of groupings, wherein for each extracted entity, the classifying is based on at least one attribute of the one or more attributes comprising the verified temporal context of the source from which the extracted entity was extracted;
• and
• generating, by the one or more processors, a corpus comprising the plurality of groupings, wherein each grouping of the plurality of groupings in the corpus comprises extracted entities with verified temporal contexts consistent with a defined time period.

A system comprising:

• a memory;
• one or more processors in communication with the memory;
• program instructions executable by the one or more processors via the memory to perform a method, the method comprising:
• ingesting, by the one or more processors, content from one or more sources of content and, for each source of the one or more sources of the content, one or more attributes comprising a verified temporal context of the source, wherein the verified temporal context attribute comprises an assurance that content associated with the verified temporal context attribute is consistent with date and time data associated with the content, wherein the assurance is based on an image in the content being consistent with the date and time data associated with the content;
• cognitively analyzing, by the one or more processors, the content, by applying one or more entity recognition algorithm, to the content, to identify and extract entities in each source;
• classifying, by the one or more processors, each extracted entity of the extracted entities in a given grouping of a plurality of groupings, wherein for each extracted entity, the classifying is based on at least one attribute of the one or more attributes comprising the verified temporal context of the source from which the extracted entity was extracted;
• and
• generating, by the one or more processors, a corpus comprising the plurality of groupings, wherein each grouping of the plurality of groupings in the corpus comprises extracted entities with verified temporal contexts consistent with a defined time period.