Triple
T7415941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Théâtre du Rond-Point |
E171129
|
entity |
| Predicate | hasTertiaryHallCapacity |
P76819
|
FINISHED |
| Object | approximately 130 |
—
|
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: approximately 130 | Statement: [Théâtre du Rond-Point, hasTertiaryHallCapacity, approximately 130]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTertiaryHallCapacity Context triple: [Théâtre du Rond-Point, hasTertiaryHallCapacity, approximately 130]
-
A.
hasSecondaryHall
Indicates that an entity is associated with or contains an additional, subordinate hall beyond its primary hall.
-
B.
mainHallCapacity
Indicates the maximum number of people that the main hall can accommodate at one time.
-
C.
hasStationHall
Indicates that one entity (typically a station) includes or is associated with a station hall area as part of its structure or facilities.
-
D.
numberOfHalls
Indicates the quantity of halls associated with a given entity or location.
-
E.
courtyardCapacity
Indicates the maximum number of entities that can be accommodated in a courtyard at the same time.
- 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_69c68a618bdc81908d8018edadecd1a4 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f2c643248190a387abba2f482b25 |
completed | March 27, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69c6f0345040819094c5756dfa487faf |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f1c3307481909a7f6bb69d4fddac |
completed | March 27, 2026, 9:08 p.m. |
Created at: March 27, 2026, 3:11 p.m.