Triple
T14901050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heald Green |
E360003
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Handforth |
E178133
|
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: Handforth | Statement: [Heald Green, adjacentTo, Handforth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Handforth Context triple: [Heald Green, adjacentTo, Handforth]
-
A.
Handforth
chosen
Handforth is a village and civil parish in Cheshire, England, situated near the town of Wilmslow and forming part of the Greater Manchester commuter belt.
-
B.
Nordhorn
Nordhorn is a town in Lower Saxony, Germany, known as the administrative center of the Grafschaft Bentheim district near the Dutch border.
-
C.
Herford
Herford is a historic town in northwestern Germany known for its medieval architecture and location in the region of North Rhine-Westphalia.
-
D.
Radevormwald
Radevormwald is a small historic town in North Rhine-Westphalia, western Germany, known for its hilly Bergisches Land landscape and traditional textile and metalworking industries.
-
E.
Wallenhorst
Wallenhorst is a municipality in Lower Saxony, Germany, located near the city of Osnabrück.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded609bf68819099ca3aa3fe1acadc |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff908410548190ada5d4f71d52919b |
completed | May 9, 2026, 7:52 p.m. |
Created at: April 10, 2026, 2:11 a.m.