Triple
T6416932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salle Le Peletier |
E127851
|
entity |
| Predicate | auditoriumType |
P70537
|
FINISHED |
| Object | horseshoe-shaped auditorium |
—
|
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: horseshoe-shaped auditorium | Statement: [Salle Le Peletier, auditoriumType, horseshoe-shaped auditorium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: auditoriumType Context triple: [Salle Le Peletier, auditoriumType, horseshoe-shaped auditorium]
-
A.
hasAuditorium
Indicates that one entity possesses or includes an auditorium as part of its facilities.
-
B.
theaterType
Indicates the specific kind or category of theater associated with an entity (e.g., cinema, opera house, drama theater).
-
C.
audienceCapacityType
Indicates the classification or type of capacity used to describe how many audience members a venue or event space can accommodate.
-
D.
theatreType
Indicates the specific category or kind of theatre associated with an entity, such as its format, style, or operational model.
-
E.
buildingTypeOfChamber
Indicates the type or category of building in which a given chamber is located or to which it belongs.
- 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_69c0083815208190a9b299b8e0640218 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c068ea06b08190901e0c0a18fd5170 |
completed | March 22, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69c060f5d4e481909d1366190607b586 |
completed | March 22, 2026, 9:36 p.m. |
| PDg | Predicate description generation | batch_69c0623e3cd48190929b0e3cba013909 |
completed | March 22, 2026, 9:42 p.m. |
Created at: March 22, 2026, 4:42 p.m.