Triple
T24591150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston Society of Film Critics Award for Best Supporting Actor |
E608541
|
entity |
| Predicate | firstWinningPerformanceFor |
P70628
|
FINISHED |
| Object | The Elephant Man |
—
|
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: The Elephant Man | Statement: [Boston Society of Film Critics Award for Best Supporting Actor, firstWinningPerformanceFor, The Elephant Man]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstWinningPerformanceFor Context triple: [Boston Society of Film Critics Award for Best Supporting Actor, firstWinningPerformanceFor, The Elephant Man]
-
A.
firstToAchieve
Indicates that one entity was the earliest or initial entity to accomplish or attain a specified goal, status, or outcome before any others.
-
B.
firstWinnerYear
Indicates the year in which an entity first won a particular competition, award, or title.
-
C.
firstRunningWinner
Indicates that the subject is the first entity to win among those participating in a running event or race.
-
D.
firstChampionshipWinEvent
Indicates the event in which an entity achieves its first-ever championship victory.
-
E.
notableFirstWinner
chosen
Indicates that the subject is the first and notably recognized winner of the object (such as an award, competition, or title).
- 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_69e2c4cf54248190af7b0c2d9ade9830 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a9db3a9481908c7a59281e2ca994 |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6c1f07081908edf0b521767e79b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:30 a.m.