Triple
T20346356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walkden railway station |
E495880
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Worsley |
—
|
NE NERFINISHED |
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: Worsley | Statement: [Walkden railway station, serves, Worsley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Worsley Context triple: [Walkden railway station, serves, Worsley]
-
A.
Worsley
chosen
Worsley is a village in Greater Manchester, England, historically significant as a coal-mining and canal hub central to the early Industrial Revolution.
-
B.
Levenshulme
Levenshulme is a residential suburb in south Manchester, England, known for its diverse community and vibrant local markets.
-
C.
Urmston
Urmston is a suburban town in Greater Manchester, England, known primarily as a residential area within the Metropolitan Borough of Trafford.
-
D.
Didsbury
Didsbury is a suburban area of Manchester, England, known for its leafy residential streets, independent shops, and vibrant café and bar scene.
-
E.
Droylsden
Droylsden is a town in Greater Manchester, England, historically part of Lancashire and now a residential suburb of Manchester.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6783937a48190ac86e4959a781a2b |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.