Triple
T4415261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dafydd |
E94953
|
entity |
| Predicate | hasVariantSpelling |
P457
|
FINISHED |
| Object | Dafyd |
E94953
|
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: Dafyd | Statement: [Dafydd, hasVariantSpelling, Dafyd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dafyd Context triple: [Dafydd, hasVariantSpelling, Dafyd]
-
A.
Dafydd
chosen
Dafydd is the Welsh form of the given name David, commonly used in Wales.
-
B.
Dafydd ap Gruffudd
Dafydd ap Gruffudd was a 13th-century Welsh prince of Gwynedd whose rebellion against English rule helped trigger the final conquest of independent Wales.
-
C.
Creiglyn Dyfi
Creiglyn Dyfi is a remote mountain lake in southern Snowdonia, Wales, known as the source of the River Dyfi and for its dramatic, rugged surroundings.
-
D.
Rhodri Morgan
Rhodri Morgan was a Welsh Labour politician who led the Welsh Government in its early years of devolution and helped shape the modern political landscape of Wales.
-
E.
Owain
Owain is a given name of Welsh origin, traditionally borne by several figures in Welsh mythology and medieval literature.
- 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_69b34539638c8190abfea3eb29425210 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b354eabb2481908ad10d21e1379e7f |
completed | March 13, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5f617012481908b8f1a9a1bc5efaf |
completed | March 14, 2026, 11:58 p.m. |
Created at: March 12, 2026, 11:29 p.m.