Triple
T979894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caerphilly County Borough |
E21142
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Rhymney
Rhymney is a former coal-mining town in the South Wales Valleys, known for its industrial heritage and location near the head of the Rhymney Valley.
|
E144320
|
NE FINISHED |
How this triple was built (4 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: Rhymney | Statement: [Caerphilly County Borough, hasSettlement, Rhymney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rhymney Context triple: [Caerphilly County Borough, hasSettlement, Rhymney]
-
A.
Treorchy
Treorchy is a former coal-mining town and community in the Rhondda Fawr valley of South Wales, known for its cultural heritage and male voice choir.
-
B.
Pencoed
Pencoed is a small town in south Wales, situated near Bridgend and known primarily as a residential and commuter community.
-
C.
Rhymney Valley
Rhymney Valley is a historic coal-mining valley in south Wales, known for its industrial heritage and communities along the River Rhymney.
-
D.
Llantrisant
Llantrisant is a historic Welsh town known for its medieval heritage and hilltop setting in South Wales.
-
E.
Glynneath
Glynneath is a small town in South Wales known for its proximity to the Brecon Beacons and local waterfalls such as Sgwd yr Eira.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rhymney Triple: [Caerphilly County Borough, hasSettlement, Rhymney]
Generated description
Rhymney is a former coal-mining town in the South Wales Valleys, known for its industrial heritage and location near the head of the Rhymney Valley.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rhymney Target entity description: Rhymney is a former coal-mining town in the South Wales Valleys, known for its industrial heritage and location near the head of the Rhymney Valley.
-
A.
Treorchy
Treorchy is a former coal-mining town and community in the Rhondda Fawr valley of South Wales, known for its cultural heritage and male voice choir.
-
B.
Pencoed
Pencoed is a small town in south Wales, situated near Bridgend and known primarily as a residential and commuter community.
-
C.
Rhymney Valley
chosen
Rhymney Valley is a historic coal-mining valley in south Wales, known for its industrial heritage and communities along the River Rhymney.
-
D.
Llantrisant
Llantrisant is a historic Welsh town known for its medieval heritage and hilltop setting in South Wales.
-
E.
Glynneath
Glynneath is a small town in South Wales known for its proximity to the Brecon Beacons and local waterfalls such as Sgwd yr Eira.
- F. None of above.
Provenance (5 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b47b58ec81908d95f151b9af3dae |
completed | March 1, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad67f0651881909314e8761a7a7a5b |
completed | March 8, 2026, 12:13 p.m. |
| NEDg | Description generation | batch_69ad6918ebd4819085cd74c172e5c72e |
completed | March 8, 2026, 12:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad697d0edc8190b94e61b57f0c65ee |
completed | March 8, 2026, 12:20 p.m. |
Created at: March 1, 2026, 7:40 p.m.