Triple
T3049350
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FEI show jumping events |
E83528
|
entity |
| Predicate | takePlaceOn |
P36317
|
FINISHED |
| Object | sand arenas |
—
|
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: sand arenas | Statement: [FEI show jumping events, takePlaceOn, sand arenas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: takePlaceOn Context triple: [FEI show jumping events, takePlaceOn, sand arenas]
-
A.
tookPlaceFrom
Indicates that an event or occurrence started or was ongoing beginning at a specified time or location.
-
B.
typicallyHeldIn
Indicates that an event, activity, or process most commonly or usually takes place within a particular location, venue, or context.
-
C.
areHeldIn
chosen
Indicates that events, activities, or objects take place or are located within a particular venue, container, or setting.
-
D.
presentsAt
Indicates that one entity delivers or gives a presentation, talk, or performance at a particular event, venue, or occasion.
-
E.
presidedAt
Indicates that one entity held a position of authority or leadership over the proceedings or activities that took place at a specific event or location.
- 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_69ad8b24924c8190a9bb6f61d519e4ae |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9bb00a348190877c9cbf0f13cba4 |
completed | March 8, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69ad962195388190856013a2519c2b0f |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.