Triple
T10098671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wellesbourne campus |
E215939
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Wellesbourne |
E627428
|
NE 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: Wellesbourne | Statement: [Wellesbourne campus, locatedIn, Wellesbourne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wellesbourne Context triple: [Wellesbourne campus, locatedIn, Wellesbourne]
-
A.
Wellesbourne
chosen
Wellesbourne is a large English village in Warwickshire, known for its historic airfield and proximity to Stratford-upon-Avon.
-
B.
Wrottesley
Wrottesley is an English surname historically associated with a prominent aristocratic family and the title Baron Wrottesley.
-
C.
Wolverley
Wolverley is a village in Worcestershire, England, known as the birthplace of the renowned 18th-century printer and typographer John Baskerville.
-
D.
Willesborough
Willesborough is a suburban district and residential area within the town of Ashford in Kent, England.
-
E.
Cornbrook
Cornbrook is a major Metrolink tram interchange area in Manchester, England, providing key connections between multiple tram lines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca83a4947c8190823a7495dc5d96ed |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd07c0e248190b4ab450e0b83ea0c |
completed | April 2, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2b6c218b08190853b0979296e2f83 |
completed | April 5, 2026, 7:23 p.m. |
Created at: March 30, 2026, 9:02 p.m.