# US 2026/0228294 A1 · Question answering using entity references in unstructured data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0228294 A1 - Document ID: US20260228294A1 - Status: Published application - Kind: A1 - Application number: 19/633,318 - Filed: 2026-03-30 - Published: 2026-08-06 - Earliest claimed: 2013-03-15 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Dvir Keysar; Tomer Shmiel - Web page: https://patentgrep.com/patent/US20260228294A1 ## CPC - G06F 16/9538: Presentation of query results - G06F 16/36: Creation of semantic tools, e.g. ontology or thesauri - G06F 16/951: Indexing; Web crawling techniques - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods, systems, and computer-readable media are provided for collective reconciliation. In some implementations, a query is received, wherein the query is associated at least in part with a type of entity. Top-ranked search results are caused to be generated based at least in part on the query. An entity of the type of entity is identified in the top-ranked results and a response to the query is generated from the top-ranked results, the response including a reference to the entity that includes text distinct from the terms of the query. ## Claims ### Claim 1 A method comprising: receiving a question query, wherein the question query is associated with a type of entity requested in the question query; generating a set of search results based on the question query, wherein each search result in the set contains unstructured text content; retrieving previously generated data associated with top-ranked search results in the set, wherein the previously generated data includes entity references found within the unstructured text content of the respective top-ranked search results, the entity references corresponding to entities of the type of entity; and generating and providing a natural language answer to the question query, wherein the natural language answer includes at least one term from the question query and text identifying an entity reference determined from the previously generated data of the top-ranked search results. ### Claim 2 (depends on 1) The method of claim 1, wherein generating the natural language answer includes incorporating, from the content of the top-ranked search results, an image corresponding to the entity reference. ### Claim 3 (depends on 1) The method of claim 1, wherein the previously generated data associates a unique identifier with the entity reference, the unique identifier used to disambiguate entity references in the unstructured text content. ### Claim 4 (depends on 3) The method of claim 3, wherein identifying the entity reference includes scoring an entity associated with the unique identifier based on a relationship between the entity reference and the unstructured text content within which the entity reference appears. ### Claim 5 (depends on 1) The method of claim 1, wherein the natural language answer is generated using at least some terms of the question query. ### Claim 6 (depends on 1) The method of claim 1, further comprising providing the natural language answer for display along with, but visually distinguished from, references to the top-ranked search results. ### Claim 7 (depends on 1) The method of claim 1, wherein an entity corresponding to the entity reference is a most frequently occurring entity in the top-ranked search results. ### Claim 8 (depends on 1) The method of claim 1, wherein generating the natural language answer includes: determining a topicality score for each entity reference, wherein the topicality score is based on a relationship between the respective entity reference and the unstructured text content in which the entity reference appears; and using the topicality score to select the text identifying the entity reference. ### Claim 9 (depends on 1) The method of claim 1, wherein generating the set of search results includes: determining that the entity reference fails to meet a degree of confidence; and in response to determining that the entity reference fails to meet the degree of confidence, adding previously generated data from lower-ordered search results to the top-ranked search results until the entity reference meets the degree of confidence. ### Claim 10 A system comprising: at least one processor; and memory storing instructions that, when executed by the at least one processor, cause the system to perform operations including: receiving a question query, wherein the question query is associated with a type of entity requested in the question query; generating a set of search results based on the question query, wherein each search result in the set contains unstructured text content; retrieving previously generated data associated with top-ranked search results in the set, wherein the previously generated data includes entity references found within the unstructured text content of the respective top-ranked search results, the entity references corresponding to entities of the type of entity; and generating and providing a natural language answer to the question query, wherein the natural language answer includes at least one term from the question query and text identifying an entity reference determined from the previously generated data of the top-ranked search results. ### Claim 11 (depends on 10) The system of claim 10, wherein generating the natural language answer includes incorporating, from the content of the top-ranked search results, an image corresponding to the entity reference. ### Claim 12 (depends on 10) The system of claim 10, wherein the previously generated data associates a unique identifier with the entity reference, the unique identifier used to disambiguate entity references in the unstructured text content. ### Claim 13 (depends on 12) The system of claim 12, wherein identifying the entity reference includes scoring an entity associated with the unique identifier based on a relationship between the entity reference and the unstructured text content within which the entity reference appears. ### Claim 14 (depends on 10) The system of claim 10, wherein the natural language answer is generated using at least some terms of the question query. ### Claim 15 (depends on 10) The system of claim 10, wherein the operations further include providing the natural language answer for display along with, but visually distinguished from, references to the top-ranked search results. ### Claim 16 (depends on 10) The system of claim 10, wherein an entity corresponding to the entity reference is a most frequently occurring entity in the top-ranked search results. ### Claim 17 (depends on 10) The system of claim 10, wherein generating the natural language answer includes: determining a topicality score for each entity reference, wherein the topicality score is based on a relationship between the respective entity reference and the unstructured text content in which the entity reference appears; and using the topicality score to select the text identifying the entity reference. ### Claim 18 (depends on 10) The system of claim 10, wherein generating the set of search results includes: determining that the entity reference fails to meet a degree of confidence; and in response to determining that the entity reference fails to meet the degree of confidence, adding previously generated data from lower-ordered search results to the top-ranked search results until the entity reference meets the degree of confidence. ### Claim 19 A non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations comprising: receiving a question query, wherein the question query is associated with a type of entity requested in the question query; generating a set of search results based on the question query, wherein each search result in the set contains unstructured text content; retrieving previously generated data associated with top-ranked search results in the set, wherein the previously generated data includes entity references found within the unstructured text content of the respective top-ranked search results, the entity references corresponding to entities of the type of entity; and generating and providing a natural language answer to the question query, wherein the natural language answer includes at least one term from the question query and text identifying an entity reference determined from the previously generated data of the top-ranked search results. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein the previously generated data associates a unique identifier with the entity reference, the unique identifier used to disambiguate entity references in the unstructured text content.