Triple
T26394589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mazda Stadium |
E663512
|
entity |
| Predicate | hasOutfieldFenceType |
P109697
|
FINISHED |
| Object | asymmetrical outfield dimensions |
—
|
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: asymmetrical outfield dimensions | Statement: [Mazda Stadium, hasOutfieldFenceType, asymmetrical outfield dimensions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOutfieldFenceType Context triple: [Mazda Stadium, hasOutfieldFenceType, asymmetrical outfield dimensions]
-
A.
hasOutfieldFeature
Indicates that an entity possesses or includes a specific feature or characteristic located in its outfield area.
-
B.
outfieldWallType
chosen
Indicates the specific kind or configuration of the wall that defines the outer boundary of an outfield area.
-
C.
outfieldWallHeight
Indicates the height of the wall that defines the boundary of the outfield area in a ballpark or playing field.
-
D.
outfieldWallDistance
Indicates the measured distance from home plate to the outfield wall at a particular point or area on the field.
-
E.
outfieldSurface
Indicates the type or condition of the playing surface specifically in the outfield area of a sports field.
- 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_69ee883823988190b418b111be28a44a |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f650c70d7c819093d9a0f005f7c8d5 |
completed | May 2, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f64cab1f648190a2a9460690d18a37 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 26, 2026, 11:28 p.m.