Triple
T12160798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tryfan |
E289699
|
entity |
| Predicate | hasNearbyPeak |
P7612
|
FINISHED |
| Object | Pen yr Ole Wen |
E853171
|
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: Pen yr Ole Wen | Statement: [Tryfan, hasNearbyPeak, Pen yr Ole Wen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pen yr Ole Wen Context triple: [Tryfan, hasNearbyPeak, Pen yr Ole Wen]
-
A.
Pen yr Ole Wen
chosen
Pen yr Ole Wen is a prominent mountain in Snowdonia, North Wales, known for its steep ascent and striking views over the Ogwen Valley.
-
B.
Pant-yr-awel
Pant-yr-awel is a small village in the Ogmore Valley in Bridgend County Borough, South Wales.
-
C.
Carn Goedog
Carn Goedog is a rocky outcrop in the Preseli Hills of Pembrokeshire, Wales, identified as a major source of the bluestone used in the construction of Stonehenge.
-
D.
Yr Wyddfa
Yr Wyddfa is the Welsh name for Snowdon, the highest and one of the most iconic mountains in Wales and the entire British Isles.
-
E.
Pont-y-Pant
Pont-y-Pant is a small rural halt railway station in North Wales serving the village of Dolwyddelan in the Conwy Valley.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915c395e48190a16e97fd29787a51 |
completed | April 10, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f6a0baf0819094e90b7e92b979d4 |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:50 p.m.