Triple
T24151068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Funny Girl (stage musical) |
E598532
|
entity |
| Predicate | originalCastAlbumPerformer |
P88314
|
FINISHED |
| Object | Barbra Streisand |
—
|
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: Barbra Streisand | Statement: [Funny Girl (stage musical), originalCastAlbumPerformer, Barbra Streisand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalCastAlbumPerformer Context triple: [Funny Girl (stage musical), originalCastAlbumPerformer, Barbra Streisand]
-
A.
originalCastAlbum
chosen
Indicates that a musical or theatrical production has an official recording featuring its original cast performing the work.
-
B.
originalCastRecordingReleaseDate
Indicates the date on which the original cast recording of a production was first released.
-
C.
originalCastPerformer
Indicates that a performer was part of the original cast in the first production or release of a work.
-
D.
hasSoundtrackPerformer
Indicates that a performer (such as an artist, band, or ensemble) is responsible for performing music on the soundtrack associated with a given work.
-
E.
performerCreditedAs
Indicates that a performer is associated with a work under a specific credited name or alias.
- 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_69e288c9e488819093dd1acd91b08b8a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e0e108308190ba8740590a1c5130 |
completed | April 29, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_69f176585f3481909beb907de252cd98 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:30 p.m.