Triple
T10749605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gellilydan |
E253538
|
entity |
| Predicate | hasNearbyFeature |
P350
|
FINISHED |
| Object | Afon Prysor |
E902625
|
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: Afon Prysor | Statement: [Gellilydan, hasNearbyFeature, Afon Prysor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Afon Prysor Context triple: [Gellilydan, hasNearbyFeature, Afon Prysor]
-
A.
Afon Prysor
chosen
Afon Prysor is a river in Gwynedd, Wales, that flows through the mountainous landscape of Snowdonia and helps drain the upland areas around Trawsfynydd.
-
B.
Afon Gafr
Afon Gafr is a small mountain stream in Snowdonia, Wales, flowing through the rugged landscape around the Llanberis Pass.
-
C.
Afon Castell
Afon Castell is a small river in Ceredigion, Wales, that feeds into the River Rheidol within the scenic Cambrian Mountains region.
-
D.
Afon Ogwr
Afon Ogwr is a river in South Wales that flows through Bridgend County Borough before reaching the Bristol Channel.
-
E.
Afon Dwyfor
Afon Dwyfor is a river in Gwynedd, Wales, that flows through the village of Llanystumdwy before reaching the sea near Criccieth.
- 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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d71dbfe5f481908eed42328447b158 |
completed | April 9, 2026, 3:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e46262a8f88190869c2161c3b10a19 |
completed | April 19, 2026, 5:04 a.m. |
Created at: April 8, 2026, 9:15 p.m.