Triple
T18910796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coalport |
E462599
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Jackfield |
—
|
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: Jackfield | Statement: [Coalport, near, Jackfield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jackfield Context triple: [Coalport, near, Jackfield]
-
A.
Jackfield
chosen
Jackfield is a historic village in Shropshire, England, known for its role in early industrial ceramics and its location along the River Severn within the Ironbridge Gorge World Heritage Site.
-
B.
Chatteris
Chatteris is a small market town in the Fenland district of Cambridgeshire, England, known for its agricultural surroundings and historic parish church.
-
C.
Annfield Plain
Annfield Plain is a former coal-mining village in County Durham, England, known for its industrial heritage in the North East.
-
D.
Austerfield
Austerfield is a small village in South Yorkshire, England, notable for its historic church and connections to early English history.
-
E.
Dockenfield
Dockenfield is a small rural village and civil parish located in the borough of Waverley in Surrey, England.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c6226f4081909b77aac26c574980 |
completed | April 20, 2026, 6:22 a.m. |
Created at: April 10, 2026, 11:58 a.m.