Triple
T6579118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carmelina |
E157245
|
entity |
| Predicate | numberOfBroadwayPreviews |
P59468
|
FINISHED |
| Object | 11 |
—
|
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: 11 | Statement: [Carmelina, numberOfBroadwayPreviews, 11]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfBroadwayPreviews Context triple: [Carmelina, numberOfBroadwayPreviews, 11]
-
A.
totalBroadwayPreviews
chosen
Indicates the total number of preview performances a Broadway production has had before its official opening.
-
B.
broadwayPreviewsBegin
Indicates the date on which a Broadway production begins its preview performances before the official opening.
-
C.
numberOfBroadwayPerformances
Indicates the total count of times a production or performance has been staged on Broadway.
-
D.
hasBroadwayOpeningContext
Indicates that an entity is associated with contextual details specifically about its Broadway opening (such as time, place, or circumstances of the premiere).
-
E.
hasBroadwayProduction
Indicates that a work or show has been produced and staged in a Broadway theater.
- 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_69c6882b3a108190b3a9eb343ae4162c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6c07cdf048190945ca5810fb1de88 |
completed | March 27, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69c6acfb462481909cb7aff5af4bca9d |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:54 p.m.