Triple
T3169828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Could Write a Book |
E66299
|
entity |
| Predicate | performingArtsDomain |
P46717
|
FINISHED |
| Object | musical theatre |
—
|
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: musical theatre | Statement: [I Could Write a Book, performingArtsDomain, musical theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performingArtsDomain Context triple: [I Could Write a Book, performingArtsDomain, musical theatre]
-
A.
performsMusicIn
Indicates that an entity presents or plays music within a particular venue, event, or context.
-
B.
presentsPerformancesBy
Indicates that one entity organizes or stages performances that feature or are carried out by another entity.
-
C.
theatre
Indicates that an entity is a theater or is associated with theatrical performances or activities.
-
D.
livePerformanceStapleFor
Indicates that something (such as a song or piece) is regularly and prominently featured in another entity’s live performances.
-
E.
performerType
Indicates the role or category of performer responsible for carrying out an action or participating in an event.
- 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada64917e08190bf0466d2c5e43790 |
completed | March 8, 2026, 4:39 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada20880e481908ecac09d49b1f1c3 |
completed | March 8, 2026, 4:21 p.m. |
Created at: March 8, 2026, 3:06 p.m.