Triple
T37106160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiddler on the Roof (1964 Broadway premiere) |
E918846
|
entity |
| Predicate | openingTheatre |
P193691
|
FINISHED |
| Object | Imperial Theatre |
—
|
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: Imperial Theatre | Statement: [Fiddler on the Roof (1964 Broadway premiere), openingTheatre, Imperial Theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingTheatre Context triple: [Fiddler on the Roof (1964 Broadway premiere), openingTheatre, Imperial Theatre]
-
A.
theatreOpened
Indicates that a theatre began operating or was officially opened at a particular time or event.
-
B.
openingTo
Indicates that one entity serves as an entrance, access point, or passage leading into or toward another entity.
-
C.
theater
Indicates that an entity is a theater or is functioning in the role of a theater (a venue where performances or films are shown).
-
D.
theatreCity
Indicates that a theatre is located in, or primarily associated with, a particular city.
-
E.
theatre
Indicates that an entity is a theater or is associated with theatrical performances or activities.
- F. None of above. chosen
Provenance (4 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
| PDg | Predicate description generation | batch_69fd4f38728c8190b3271abc80882cfb |
completed | May 8, 2026, 2:49 a.m. |
Created at: May 3, 2026, 4:14 p.m.