Triple
T28040547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macerata Opera Festival |
E708525
|
entity |
| Predicate | hasOpenAirFeature |
P47415
|
FINISHED |
| Object | no permanent roof over audience |
—
|
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: no permanent roof over audience | Statement: [Macerata Opera Festival, hasOpenAirFeature, no permanent roof over audience]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOpenAirFeature Context triple: [Macerata Opera Festival, hasOpenAirFeature, no permanent roof over audience]
-
A.
hasOpeningToSky
Indicates that one entity has an opening or aperture that is directly exposed to the sky.
-
B.
hasOpenAirTerminals
Indicates that an entity possesses terminals or facilities that are located outdoors or in open-air environments rather than fully enclosed structures.
-
C.
hasOutdoorSpaceType
Indicates the specific kind of outdoor area associated with an entity, such as a balcony, terrace, garden, or patio.
-
D.
hasPublicSpaces
Indicates that an entity includes or provides areas that are accessible and usable by the general public.
-
E.
isOpenAir
chosen
Indicates that something takes place or exists in an outdoor, unenclosed environment exposed to open air.
- 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 27, 2026, 8:25 p.m.