Triple
T10570946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corwen |
E249477
|
entity |
| Predicate | hasReligiousBuilding |
P1191
|
FINISHED |
| Object | Capel Seion |
E270153
|
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: Capel Seion | Statement: [Corwen, hasReligiousBuilding, Capel Seion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Capel Seion Context triple: [Corwen, hasReligiousBuilding, Capel Seion]
-
A.
Capel Seion
chosen
Capel Seion is a chapel serving the local religious community in the town of Corwen, Wales.
-
B.
Capel Tegid
Capel Tegid is a chapel in the town of Bala in Gwynedd, Wales, serving as a local Christian place of worship.
-
C.
Capel Curig
Capel Curig is a small village in North Wales that serves as a popular base for outdoor activities and mountain walking in the Snowdonia region.
-
D.
Capel Bangor
Capel Bangor is a small village in Ceredigion, Wales, situated in the scenic Rheidol Valley east of Aberystwyth.
-
E.
Penrhyn
Penrhyn is the largest and one of the most remote atolls in the Cook Islands, known for its expansive lagoon and traditional Polynesian culture.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5274678148190b7a1afc099628357 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98838c9b88190b12d8873695e219e |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 6, 2026, 12:37 p.m.