Triple
T17462849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caerwent |
E425197
|
entity |
| Predicate | hasNearbyTown |
P3883
|
FINISHED |
| Object | Caldicot |
—
|
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: Caldicot | Statement: [Caerwent, hasNearbyTown, Caldicot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caldicot Context triple: [Caerwent, hasNearbyTown, Caldicot]
-
A.
Caldicot
chosen
Caldicot is a town in Monmouthshire, South Wales, known for its medieval castle and proximity to the Severn Estuary.
-
B.
Cwmavon
Cwmavon is a village in Neath Port Talbot, South Wales, situated near Port Talbot and known for its industrial heritage and surrounding valleys.
-
C.
Cwmavon
Cwmavon is a village in South Wales that forms part of the historic Blaenavon Industrial Landscape, a UNESCO World Heritage Site linked to the region’s coal and iron industries.
-
D.
Pencoed
Pencoed is a small town in south Wales, situated near Bridgend and known primarily as a residential and commuter community.
-
E.
Penclawdd
Penclawdd is a coastal village on the Gower Peninsula in South Wales, historically known for its cockle industry and views over the Loughor Estuary.
- 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_69d889dbc2e88190b18ea6115e819258 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451a4c36c81909c7c4b1b0d976921 |
completed | April 19, 2026, 3:53 a.m. |
Created at: April 10, 2026, 5:47 a.m.