Triple
T34181862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank T.J. Mackey |
E876841
|
entity |
| Predicate | portrayedByReceivedNomination |
P25708
|
FINISHED |
| Object | Academy Award for Best Supporting Actor |
—
|
NE NERFINISHED |
How this triple was built (2 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: Academy Award for Best Supporting Actor | Statement: [Frank T.J. Mackey, portrayedByReceivedNomination, Academy Award for Best Supporting Actor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedByReceivedNomination Context triple: [Frank T.J. Mackey, portrayedByReceivedNomination, Academy Award for Best Supporting Actor]
-
A.
nomineeOf
Indicates that one entity is a candidate put forward or selected for an award, position, or recognition by another entity.
-
B.
nominationReceivedBy
chosen
Indicates that an entity has received a nomination from another entity or source.
-
C.
portrayedByWonAward
Indicates that the person who portrayed a character or role received an award for that performance.
-
D.
hasNomineeRole
Indicates that an entity serves in or holds a specific nominee role or position in relation to another entity.
-
E.
portrayedByAwardStatusAtRelease
Indicates that the subject is portrayed by an entity whose award status (e.g., nominated, winning, none) is specified as it was at the time of the work’s release.
- F. None of above.
Provenance (3 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_69f349ae640c8190b9cd220b5368d8b6 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff0b6bc4a88190bf1d38c6ea26bcdc |
completed | May 9, 2026, 10:24 a.m. |
| PD | Predicate disambiguation | batch_69ff082a22f4819095ded971dbd8ea7b |
completed | May 9, 2026, 10:10 a.m. |
Created at: May 1, 2026, 1:54 a.m.