Triple
T23322850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Park Lane |
E591201
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Hazel Grove |
—
|
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: Hazel Grove | Statement: [Park Lane, hasNearbySettlement, Hazel Grove]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hazel Grove Context triple: [Park Lane, hasNearbySettlement, Hazel Grove]
-
A.
Hazel Grove
chosen
Hazel Grove is a suburban town in Greater Manchester, England, known as a residential and commuter area on the outskirts of Stockport.
-
B.
Hazeldean
Hazeldean is a rural locality and small town situated within Queensland’s Somerset Region in Australia.
-
C.
Hazel Grove–Buxton
Hazel Grove–Buxton is a rural section of the Manchester–Buxton railway line in northwest England, known for its scenic Peak District landscapes and diesel-operated passenger services.
-
D.
Sandycroft
Sandycroft is a village in the Deeside area of Flintshire, Wales, known primarily as a residential community with local amenities and light industry.
-
E.
Harlow Town
Harlow Town is a railway station in Essex, England, serving the town of Harlow on the West Anglia Main Line with regional and commuter services to London and other destinations.
- 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1978731b0819090f92ef768f2a749 |
completed | April 29, 2026, 5:30 a.m. |
Created at: April 17, 2026, 5:07 p.m.