Triple
T2007605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swing Time |
E43619
|
entity |
| Predicate | songWonAward |
P31988
|
FINISHED |
| Object | The Way You Look Tonight – Academy Award for Best Original Song |
—
|
LITERAL FINISHED |
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 Way You Look Tonight – Academy Award for Best Original Song | Statement: [Swing Time, songWonAward, The Way You Look Tonight – Academy Award for Best Original Song]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: songWonAward Context triple: [Swing Time, songWonAward, The Way You Look Tonight – Academy Award for Best Original Song]
-
A.
awardReceived
Indicates that an entity has been granted or honored with a specific award or recognition.
-
B.
awardReceivedForTrack
chosen
Indicates that an award was received specifically in recognition of a particular track (e.g., song or recording).
-
C.
awardConferred
Indicates that an award or honor has been formally granted by one entity to another.
-
D.
awardFor
Indicates that something is given or granted as recognition or a prize for a particular achievement, work, or contribution.
-
E.
notableAwardWon
Indicates that an entity has received a specific notable award as a winner.
- 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_69a88716e9f08190946313fdc949e3cf |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb89aca908190b8b659af65afdf6f |
completed | March 7, 2026, 5:33 a.m. |
| PD | Predicate disambiguation | batch_69abb79e63c08190982c8b44a557266f |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:37 p.m.