Triple
T18812496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albany, Auckland |
E460049
|
entity |
| Predicate | sportsFacilityTypeNearby |
P25287
|
FINISHED |
| Object | multi-purpose stadium |
—
|
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: multi-purpose stadium | Statement: [Albany, Auckland, sportsFacilityTypeNearby, multi-purpose stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportsFacilityTypeNearby Context triple: [Albany, Auckland, sportsFacilityTypeNearby, multi-purpose stadium]
-
A.
sportsFacility
Indicates that one entity is a sports facility where sports or physical activities can take place for the other entity.
-
B.
placeOfSportsActivity
Indicates the location where a sports activity is or was carried out.
-
C.
sportsVenueFor
Indicates that a venue is used as the location or facility where a particular sport or sporting event takes place.
-
D.
hasSportsVenueType
chosen
Indicates that a sports venue is classified as being of a specific type or category (e.g., stadium, arena, court).
-
E.
Game4Venue
Indicates that a particular game is scheduled to take place at a specific venue.
- 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_69d8d398c7d4819091cb2f7e48948aeb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a3dcc7d88190801d9c9202e0e411 |
completed | April 20, 2026, 3:56 a.m. |
| PD | Predicate disambiguation | batch_69e48d1b10ec8190985c6fb5766ff981 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:53 a.m.