Triple
T588600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold Prince Theatre |
E17215
|
entity |
| Predicate | namedForOccupationOfHonoree |
P365
|
FINISHED |
| Object | Broadway producer |
—
|
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: Broadway producer | Statement: [Harold Prince Theatre, namedForOccupationOfHonoree, Broadway producer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: namedForOccupationOfHonoree Context triple: [Harold Prince Theatre, namedForOccupationOfHonoree, Broadway producer]
-
A.
namedPersonOccupation
Indicates that a person is explicitly identified as having a particular occupation or job role.
-
B.
namedPersonRole
Indicates that a person is identified by name as holding a specific role or position in a given context.
-
C.
hasNotableHonoree
Indicates that an entity is notably dedicated to, named after, or honors a particular person or group.
-
D.
namesakeOccupation
chosen
Indicates that one entity’s occupation is the same as, or derived from, the occupation associated with the other entity’s namesake.
-
E.
occupationOf
Indicates that one entity holds or performs the job, role, or profession associated with another entity.
- 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_69a49379d09c8190ac7e00b24e2810b1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49b9d1e68819096a9b5e7b2e83d6e |
completed | March 1, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69a494ca68448190a516b9c3525d8916 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.