Triple
T23227485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I vespri siciliani |
E581051
|
entity |
| Predicate | premiereVenueType |
P117072
|
FINISHED |
| Object | opera house |
—
|
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: opera house | Statement: [I vespri siciliani, premiereVenueType, opera house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: premiereVenueType Context triple: [I vespri siciliani, premiereVenueType, opera house]
-
A.
internationalVenueFor
Indicates that a location serves as a host or site for events, activities, or functions involving participants or audiences from multiple countries.
-
B.
screeningVenue
Indicates the place or location where a screening (such as a film or event showing) takes place.
-
C.
premiereType
Indicates the specific kind or category of a premiere event associated with an entity (such as world premiere, national premiere, or regional premiere).
-
D.
intendedPerformanceVenue
Indicates the venue or location where a performance is planned or intended to take place.
-
E.
recordedAtVenueType
chosen
Indicates that an event or recording took place at a venue of a specified type (e.g., studio, concert hall, stadium).
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922f5b4081908145d66ea7534493 |
completed | April 29, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:09 p.m.