Triple
T5058770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coedffranc North |
E113971
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Llansamlet |
E401994
|
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: Llansamlet | Statement: [Coedffranc North, adjacentTo, Llansamlet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Llansamlet Context triple: [Coedffranc North, adjacentTo, Llansamlet]
-
A.
Llansamlet
chosen
Llansamlet is a suburban district and electoral ward situated to the northeast of Swansea in South Wales.
-
B.
Llantarnam
Llantarnam is a residential suburb and historic area within the town of Cwmbran in South Wales.
-
C.
Llanelltyd
Llanelltyd is a small historic village in Gwynedd, Wales, known for its scenic setting near Dolgellau and the ruins of Cymer Abbey.
-
D.
Llanbadoc
Llanbadoc is a small village in Monmouthshire, southeast Wales, best known as the birthplace of naturalist Alfred Russel Wallace.
-
E.
Nant Gwynant
Nant Gwynant is a scenic valley in Snowdonia, Wales, known for its lakes, mountain views, and popular hiking routes near Snowdon.
- 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_69bd443aa1f88190abb992d138f2cf42 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74523434819092b8b15992073b5b |
completed | March 20, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bea48fa2dc8190810eebc136d4859a |
completed | March 21, 2026, 2 p.m. |
Created at: March 20, 2026, 1:38 p.m.