Triple
T15297639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannop Ponds |
E365699
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Coleford |
E365913
|
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: Coleford | Statement: [Cannop Ponds, near, Coleford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coleford Context triple: [Cannop Ponds, near, Coleford]
-
A.
Coleford
chosen
Coleford is a historic market town in Gloucestershire, England, serving as one of the main settlements in and around the Forest of Dean.
-
B.
Whitland
Whitland is a small market town in Carmarthenshire, southwest Wales, known historically for its nearby Cistercian abbey and its role as a local agricultural and transport hub.
-
C.
Ammanford
Ammanford is a former coal-mining town and commercial centre in Carmarthenshire, southwest Wales.
-
D.
Cloughfold
Cloughfold is a small village in Lancashire, England, situated within the Rossendale Valley and historically associated with the region’s textile and industrial heritage.
-
E.
Skenfrith
Skenfrith is a small village in Monmouthshire, Wales, known for its historic riverside setting and its prominent medieval castle.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03686bfb8819080ba0caae652170a |
completed | April 16, 2026, 1:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fef89bb46481908f27fa98eb6ac5c3 |
completed | May 9, 2026, 9:04 a.m. |
Created at: April 10, 2026, 3:15 a.m.