Language model-based entity extraction and resolution

A computerized method, performed by a computing system having one or more hardware computer processors and one or more computer-readable storage devices storing software instructions executable by the computing system, the computerized method comprising:

• receiving first text data from a data source;
• generating a first prompt for a large language model (“LLM”), the first prompt comprising the first text data;
• transmitting the first prompt to the LLM;
• receiving a first output from the LLM in response to the first prompt, the first output comprising first one or more identification numbers that identify first one or more semantically related text portions of the first text data, the first one or more semantically related text portions comprising a first semantically related text portion;
• generating, based at least on the first output, a second prompt for a large language model (“LLM”), the second prompt comprising (i) a first part of the first semantically related text portion and (ii) first one or more suggested entities associated with the first part of the first semantically related text portion;
• transmitting the second prompt to the LLM;
• and
• receiving a second output from the LLM in response to the second prompt, the second output comprising (i) first one or more entities extracted by the LLM from the first part of the first semantically related text portion and (ii) first metadata or context associated with the first one or more entities.