Triple
T10400222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cwm Nantcol |
E245125
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Cwm Bychan |
E865282
|
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: Cwm Bychan | Statement: [Cwm Nantcol, near, Cwm Bychan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cwm Bychan Context triple: [Cwm Nantcol, near, Cwm Bychan]
-
A.
Cwm Bychan
chosen
Cwm Bychan is a remote valley in Snowdonia, Wales, known for its scenic lake, surrounding mountains, and access to historic routes like the Roman Steps.
-
B.
Cwm Cynwyn
Cwm Cynwyn is a secluded glacial valley in the Brecon Beacons of Wales, known for its steep grassy slopes and dramatic mountain scenery.
-
C.
Cwm Oergwm
Cwm Oergwm is a glacial valley in the Brecon Beacons of Wales, known for its steep sides, remote feel, and scenic mountain surroundings.
-
D.
Cwm Cloch
Cwm Cloch is a valley in Snowdonia, Wales, known as a starting point for hiking routes up the mountain Moel Hebog.
-
E.
Cwm Gwdi
Cwm Gwdi is a popular upland car park and access point in the Brecon Beacons used as a starting base for hikes onto the central Beacons peaks.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9d2e8488190b2bb8f8509903804 |
completed | April 7, 2026, 11:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9987838ac8190a6ba09305fc27621 |
completed | April 11, 2026, 12:40 a.m. |
Created at: April 6, 2026, 12:07 p.m.