Developing event-specific provisional knowledge graphs

1. A method implemented using one or more processors, comprising:

identifying a cluster of semantically-related textual snippets, composed by a plurality of users, that are transmitted over one or more computer networks;

based on the cluster of semantically-related textual snippets, newly detecting a developing event and identifying one or more entities associated with the newly-detected developing event, wherein one or more of the identified entities form part of a general-purpose knowledge graph that includes a plurality of entity nodes and a plurality of edges between the plurality of entity nodes, wherein the plurality of entity nodes of the general-purpose knowledge graph represent entities and the plurality of edges represent relationships between entities;

in response to newly detecting the developing event, and based on the identified one or more entities, constructing an event-specific provisional knowledge graph associated with the newly-detected developing event,

wherein the event-specific provisional knowledge graph shares one or more entity nodes with the general-purpose knowledge graph, and

wherein the event-specific provisional knowledge graph includes one or more additional nodes and edges, not found in the general-purpose knowledge graph, that convey a relationship between one or more of the identified entities and the developing event; and

subsequent to the constructing, querying the event-specific provisional knowledge graph for new information about the newly-detected developing event; and

causing one or more computing devices to render, as output, the new information.

2. The method of claim 1 , further comprising:

receiving a user query seeking information relating to the developing event;

wherein the querying comprises querying the event-specific provisional knowledge graph based on the user query.

3. The method of claim 1 , further comprising determining, prior to the newly detecting, that the general-purpose knowledge graph does not include information responsive to a user query.

4. The method of claim 3 , wherein the newly-detecting is responsive to the determining that the general-purpose knowledge graph does not include information responsive to the user query.

5. The method of claim 1 , wherein the cluster of semantically-related textual snippets includes a plurality of user-submitted queries.

6. The method of claim 1 , wherein the cluster of semantically-related textual snippets includes a plurality of social media posts.

7. The method of claim 1 , wherein the cluster of semantically-related textual snippets includes at least one user-submitted query and at least one social media post.

8. The method of claim 1 , further comprising monitoring one or more live data streams in response to the newly-detecting, wherein the constructing includes obtaining information from one or more of the live data streams for inclusion in the event-specific provisional knowledge graph.

9. A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions, cause the one or more processors to:

identify a cluster of semantically-related textual snippets, composed by a plurality of users, that are transmitted over one or more computer networks;

based on the cluster of semantically-related textual snippets, newly detect a developing event and identify one or more entities associated with the newly-detected developing event, wherein one or more of the identified entities form part of a general-purpose knowledge graph that includes a plurality of entity nodes and a plurality of edges between the plurality of entity nodes, wherein the plurality of entity nodes of the general-purpose knowledge graph represent entities and the plurality of edges represent relationships between entities;

in response to detection of the developing event, and based on the identified one or more entities, construct an event-specific provisional knowledge graph associated with the newly-detected developing event,

wherein the event-specific provisional knowledge graph shares one or more entity nodes with the general-purpose knowledge graph, and

wherein the event-specific provisional knowledge graph includes one or more additional nodes and edges, not found in the general-purpose knowledge graph, that convey a relationship between one or more of the identified entities and the developing event; and

subsequent to construction of the event-specific provisional knowledge graph, query the event-specific provisional knowledge graph for new information about the newly-detected developing event; and

cause one or more computing devices to render, as output, the new information.

10. The system of claim 9 , further comprising instructions to:

receive a user query seeking information relating to the developing event;

wherein the event-specific provisional knowledge graph is queried based on the user query.

11. The system of claim 9 , further comprising instructions to determine, prior to the newly detecting, that the general-purpose knowledge graph does not include information responsive to a user query.

12. The system of claim 11 , wherein the new detection is responsive to the determining that the general-purpose knowledge graph does not include information responsive to the user query.

13. The system of claim 9 , wherein the cluster of semantically-related textual snippets includes a plurality of user-submitted queries.

14. The system of claim 9 , wherein the cluster of semantically-related textual snippets includes a plurality of social media posts.

15. The system of claim 9 , wherein the cluster of semantically-related textual snippets includes at least one user-submitted query and at least one social media post.

16. The system of claim 9 , further comprising instructions to monitor one or more live data streams in response to the newly-detecting, wherein the instructions to construct the event-specific provisional knowledge graph include instructions to obtain information from one or more of the live data streams for inclusion in the event-specific provisional knowledge graph.

17. A non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a processor, cause the processor to:

identify a cluster of semantically-related textual snippets, composed by a plurality of users, that are transmitted over one or more computer networks;

based on the cluster of semantically-related textual snippets, newly detect a developing event and identifying one or more entities associated with the newly-detected developing event, wherein one or more of the identified entities form part of a general-purpose knowledge graph that includes a plurality of entity nodes and a plurality of edges between the plurality of entity nodes, wherein the plurality of entity nodes of the general-purpose knowledge graph represent entities and the plurality of edges represent relationships between entities;

in response to detection of the developing event, and based on the identified one or more entities, construct an event-specific provisional knowledge graph associated with the newly-detected developing event,

wherein the event-specific provisional knowledge graph shares one or more entity nodes with the general-purpose knowledge graph, and

wherein the event-specific provisional knowledge graph includes one or more additional nodes and edges, not found in the general-purpose knowledge graph, that convey a relationship between one or more of the identified entities and the developing event; and

subsequent to construction of the event-specific provisional knowledge graph, query the event-specific provisional knowledge graph for new information about the newly-detected developing event; and

cause one or more computing devices to render, as output, the new information.

18. The non-transitory computer-readable medium of claim 17 , further comprising instructions to:

receive a user query seeking information relating to the developing event;

wherein the event-specific provisional knowledge graph is queried based on the user query.

19. The non-transitory computer-readable medium of claim 18 , wherein the new detection is responsive to the determining that the general-purpose knowledge graph does not include information responsive to the user query.

20. The non-transitory computer-readable medium of claim 17 , further comprising instructions to determine, prior to the newly detecting, that the general-purpose knowledge graph does not include information responsive to a user query.