Triple
T22803658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tag (2018 film) |
E564469
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object |
Kevin Sable
Kevin Sable is a character in the 2018 comedy film "Tag," which follows a group of friends engaged in an elaborate, decades-long game of tag.
|
E1555786
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kevin Sable | Statement: [Tag (2018 film), notableCharacter, Kevin Sable]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Sable Context triple: [Tag (2018 film), notableCharacter, Kevin Sable]
-
A.
Kevin Gable
Kevin Gable is the bumbling yet well-meaning retired police officer and family man portrayed by Kevin James in the sitcom "Kevin Can Wait."
-
B.
Paul Hager
Paul Hager is a relatively obscure individual whose primary public mention appears to be as a namesake in reference data, with no widely documented achievements or biography.
-
C.
Brent Goldberg
Brent Goldberg is a screenwriter best known for co-writing the college comedy film "Van Wilder."
-
D.
John Briscoe
John Briscoe was a renowned engineer and water resources expert recognized globally for his contributions to water management and policy.
-
E.
Mike Kershaw
Mike Kershaw is a software developer best known for creating the wireless network detector and sniffer tool Kismet.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kevin Sable Triple: [Tag (2018 film), notableCharacter, Kevin Sable]
Generated description
Kevin Sable is a character in the 2018 comedy film "Tag," which follows a group of friends engaged in an elaborate, decades-long game of tag.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kevin Sable Target entity description: Kevin Sable is a character in the 2018 comedy film "Tag," which follows a group of friends engaged in an elaborate, decades-long game of tag.
-
A.
Kevin Gable
Kevin Gable is the bumbling yet well-meaning retired police officer and family man portrayed by Kevin James in the sitcom "Kevin Can Wait."
-
B.
Paul Hager
Paul Hager is a relatively obscure individual whose primary public mention appears to be as a namesake in reference data, with no widely documented achievements or biography.
-
C.
Brent Goldberg
Brent Goldberg is a screenwriter best known for co-writing the college comedy film "Van Wilder."
-
D.
John Briscoe
John Briscoe was a renowned engineer and water resources expert recognized globally for his contributions to water management and policy.
-
E.
Mike Kershaw
Mike Kershaw is a software developer best known for creating the wireless network detector and sniffer tool Kismet.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e245823f4c8190ade442cdcc2c224a |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17d5a7c2881909a7aaacddd09f00c |
completed | April 29, 2026, 3:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b9e9b35e08190a3ad478355279253 |
completed | May 18, 2026, 11:19 p.m. |
| NEDg | Description generation | batch_6a0ba2386bf88190911fe2cd9870023a |
completed | May 18, 2026, 11:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ba2bae9888190a8d115579643695b |
completed | May 18, 2026, 11:37 p.m. |
Created at: April 17, 2026, 3:31 p.m.