Triple
T9300518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WN6 |
E223746
|
entity |
| Predicate | covers |
P1393
|
FINISHED |
| Object | Shevington |
E223755
|
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: Shevington | Statement: [WN6, covers, Shevington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shevington Context triple: [WN6, covers, Shevington]
-
A.
Shevington
chosen
Shevington is a village and civil parish in the Metropolitan Borough of Wigan, Greater Manchester, England.
-
B.
Totton
Totton is a town in Hampshire, England, situated near the River Test on the outskirts of the New Forest and close to the city of Southampton.
-
C.
Wroughton
Wroughton is a large village and civil parish in Wiltshire, England, situated just south of the town of Swindon.
-
D.
Banwell
Banwell is a village and civil parish in North Somerset, England, known for its historic caves and medieval architecture.
-
E.
Northbourne
Northbourne is a small village and civil parish in Kent, England, known for its rural character and historic church.
- 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd08d1d954819098be177addafa406 |
completed | April 1, 2026, noon |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b26302608190a59f3ed0694ce6d9 |
completed | April 4, 2026, 6:40 a.m. |
Created at: March 30, 2026, 7:36 p.m.