System and method for name entity disambiguation with latent topic and deep graph analysis

A method for entity disambiguation, wherein the method is implemented using a system comprising a server arrangement communicably coupled to a database arrangement, wherein the database arrangement comprises a plurality of documents, wherein the method comprises:

• generating an entity network by parsing the plurality of documents, wherein the entity network comprises a plurality of entities and their relationships, the plurality of entities comprising at least:
• document entities, name entities and topic entities, wherein the entity network is generated by:
• determining latent features relating to the plurality of documents and identifying relationships between the latent features and at least one document entity;
• determining an importance score of each of the name entities using centrality algorithms;
• determining a relevance score of at least one document entity based on relationships thereof with the name entities and the topic entities, and the importance score of each of the name entities using link analysis algorithms;
• clustering one or more name entities based on the relationships therebetween using clustering coefficients;
• assigning a name entity from each cluster of the one or more name entities as the person entity based on the importance score of each of the name entities;
• and
• employing contextual information determined for the entity network to be used in a mathematical model for entity disambiguation.