Triple
T16389673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Llwybr Taf |
E398016
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Brecon |
E230273
|
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: Brecon | Statement: [Llwybr Taf, connects, Brecon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brecon Context triple: [Llwybr Taf, connects, Brecon]
-
A.
Brecon
chosen
Brecon is a historic market town in Powys, mid Wales, known for its cathedral, Georgian architecture, and location near the Brecon Beacons National Park.
-
B.
Builth Wells
Builth Wells is a small market town in Powys, mid Wales, known for its rural setting and proximity to the Royal Welsh Showground.
-
C.
Cwmtwrch
Cwmtwrch is a small village in the upper Swansea Valley in Wales, known for its rural setting and proximity to the Brecon Beacons.
-
D.
Abergavenny
Abergavenny is a historic market town in Monmouthshire, Wales, known as a gateway to the Brecon Beacons and for its annual food festival.
-
E.
Coelbren
Coelbren is a small village in Powys, Wales, situated near the Brecon Beacons and known as a gateway to local waterfalls and scenic walking routes.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e326414f44819093ebc11f1b63444c |
completed | April 18, 2026, 6:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c32b4a88190a07db59965b38890 |
completed | May 11, 2026, 7:58 a.m. |
Created at: April 10, 2026, 5:08 a.m.