Triple
T6021087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hayfield |
E134064
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | New Mills |
E113154
|
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: New Mills | Statement: [Hayfield, near, New Mills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New Mills Context triple: [Hayfield, near, New Mills]
-
A.
New Mills
chosen
New Mills is a small town in the High Peak district of Derbyshire, England, known for its dramatic gorge, historic mills, and surrounding Peak District scenery.
-
B.
Madeley
Madeley is a town in Shropshire, England, historically associated with coal mining and now part of the new town of Telford.
-
C.
Burslem
Burslem is a town in Stoke-on-Trent, England, historically known as a major center of the pottery industry.
-
D.
Glossop
Glossop is a market town in Derbyshire, England, situated on the edge of the Peak District and historically associated with the textile industry.
-
E.
Broseley Pipeworks
Broseley Pipeworks is a historic industrial site in Shropshire, England, known for its former clay tobacco pipe factory and preserved Victorian-era workshops.
- 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_69c008742a5c8190b9cb9c2787a3d8b3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04fba86a48190984e95d5adf7c7f1 |
completed | March 22, 2026, 8:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c108c2e1c88190a1629c6438f6c8bd |
completed | March 23, 2026, 9:32 a.m. |
Created at: March 22, 2026, 4:07 p.m.