Triple
T8919991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Witney United F.C. |
E212388
|
entity |
| Predicate | geographicCoordinatePrecision |
P55602
|
FINISHED |
| Object | stadium-level |
—
|
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: stadium-level | Statement: [Witney United F.C., geographicCoordinatePrecision, stadium-level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geographicCoordinatePrecision Context triple: [Witney United F.C., geographicCoordinatePrecision, stadium-level]
-
A.
typicalHorizontalAccuracy
Indicates the usual or expected degree of precision in the horizontal (x–y) position of a measurement or location estimate.
-
B.
minimumGeoTargetingAccuracy
chosen
Indicates the lowest acceptable level of geographic precision required when targeting locations for an action or relationship.
-
C.
elevationAccuracy
Indicates the degree of precision or reliability associated with a measured or reported elevation value in the relationship.
-
D.
coordinateLatitude
Indicates the north–south geographic position of an entity on the Earth’s surface, expressed as a latitude coordinate.
-
E.
hasGeocode
Indicates that an entity is associated with a specific geographic coordinate or coded location reference.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc664f099c8190be6d20a4574212ca |
completed | April 1, 2026, 12:26 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed0ef3c81908cc69eac852ee12a |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:56 p.m.