Triple
T30409963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olympic Aquatics Stadium site |
E773589
|
entity |
| Predicate | formerVenueOf |
P149814
|
FINISHED |
| Object | Olympic Aquatics Stadium |
—
|
NE NERFINISHED |
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: Olympic Aquatics Stadium | Statement: [Olympic Aquatics Stadium site, formerVenueOf, Olympic Aquatics Stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerVenueOf Context triple: [Olympic Aquatics Stadium site, formerVenueOf, Olympic Aquatics Stadium]
-
A.
formerVenueComponentOf
Indicates that a venue previously functioned as a component or part of a larger venue or venue complex, but no longer holds that status.
-
B.
formerVenueLocation
chosen
Indicates that a location previously served as the venue for an entity or event but no longer does so.
-
C.
previousVenue
Indicates that one venue was used or occupied before another in a sequence of venues.
-
D.
venueFormerName
Indicates that a venue previously had a different official name than it has currently.
-
E.
hasFormerVenueType
Indicates that an entity previously had a specific type of venue, but that venue type is no longer current.
- 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_69f22490b8b48190ab10c886a8d58c89 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fee691952c8190822da83e46311d1d |
completed | May 9, 2026, 7:47 a.m. |
| PD | Predicate disambiguation | batch_69fee62f285c8190a625562a9b80526e |
completed | May 9, 2026, 7:45 a.m. |
Created at: April 29, 2026, 8:04 p.m.