Triple
T33063729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | So Big/So Small |
E846039
|
entity |
| Predicate | yearOfBroadwayPremiereContext |
P22746
|
FINISHED |
| Object | 2016 |
—
|
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: 2016 | Statement: [So Big/So Small, yearOfBroadwayPremiereContext, 2016]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearOfBroadwayPremiereContext Context triple: [So Big/So Small, yearOfBroadwayPremiereContext, 2016]
-
A.
offBroadwayPremiereYear
Indicates the year in which a work (such as a play or musical) first premiered in an Off-Broadway production.
-
B.
hasBroadwayOpeningYearOfSource
Indicates that the Broadway production associated with the subject entity opened in the same year as specified by the source entity.
-
C.
originalBroadwayOpeningDate
Indicates the calendar date on which a production first opened on Broadway in its original run.
-
D.
firstBroadwayProductionYear
chosen
Indicates the calendar year in which an entity’s first production was staged on Broadway.
-
E.
broadwayOpeningYearOfParentWork
Indicates the year in which the parent work of a given production or adaptation first opened on Broadway.
- 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_69f3495333b8819095e9af56855b9061 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd5bf69acc819092a01e4259785dc3 |
completed | May 8, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69fd59b3f4ac8190a7f9dd3142da6e09 |
completed | May 8, 2026, 3:34 a.m. |
Created at: May 1, 2026, 1:25 a.m.