Triple
T22840604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unbelievable |
E566067
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Austin Hébert
Austin Hébert is an American actor known for his work in film and television, including a role in the drama series "Unbelievable."
|
E1557692
|
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: Austin Hébert | Statement: [Unbelievable, stars, Austin Hébert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Austin Hébert Context triple: [Unbelievable, stars, Austin Hébert]
-
A.
Pierre Garçon
Pierre Garçon is a former NFL wide receiver best known for his productive stints with the Indianapolis Colts and Washington Redskins.
-
B.
Allen George
Allen George is a writer best known for his work on the film "Fade."
-
C.
Jerome Tang
Jerome Tang is an American college basketball coach best known for revitalizing the Kansas State Wildcats men's basketball program after a long tenure as an assistant at Baylor.
-
D.
Quenton Nelson
Quenton Nelson is an American football guard in the NFL, best known as a dominant All-Pro lineman for the Indianapolis Colts.
-
E.
Bestor Robinson
Bestor Robinson was an American mountaineer, attorney, and conservationist known for pioneering climbs in the American Southwest and his leadership in the Sierra Club.
- 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: Austin Hébert Triple: [Unbelievable, stars, Austin Hébert]
Generated description
Austin Hébert is an American actor known for his work in film and television, including a role in the drama series "Unbelievable."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Austin Hébert Target entity description: Austin Hébert is an American actor known for his work in film and television, including a role in the drama series "Unbelievable."
-
A.
Pierre Garçon
Pierre Garçon is a former NFL wide receiver best known for his productive stints with the Indianapolis Colts and Washington Redskins.
-
B.
Allen George
Allen George is a writer best known for his work on the film "Fade."
-
C.
Jerome Tang
Jerome Tang is an American college basketball coach best known for revitalizing the Kansas State Wildcats men's basketball program after a long tenure as an assistant at Baylor.
-
D.
Quenton Nelson
Quenton Nelson is an American football guard in the NFL, best known as a dominant All-Pro lineman for the Indianapolis Colts.
-
E.
Bestor Robinson
Bestor Robinson was an American mountaineer, attorney, and conservationist known for pioneering climbs in the American Southwest and his leadership in the Sierra Club.
- 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e83fa48819084568264ef45c833 |
completed | April 29, 2026, 3:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ba7b565388190bb70602834ae5622 |
completed | May 18, 2026, 11:58 p.m. |
| NEDg | Description generation | batch_6a0ba8666f608190b512aa4c8442f6c1 |
completed | May 19, 2026, 12:01 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0baa4decf881909774facad2cae93d |
completed | May 19, 2026, 12:09 a.m. |
Created at: April 17, 2026, 3:35 p.m.