Triple
T19154006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Llewelyn Thomas |
E468878
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Llewelyn |
—
|
NE NERFINISHED |
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: Llewelyn | Statement: [Llewelyn Thomas, givenName, Llewelyn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Llewelyn Context triple: [Llewelyn Thomas, givenName, Llewelyn]
-
A.
Llewelyn
chosen
Llewelyn is a Welsh given name of Celtic origin traditionally used for males.
-
B.
Llywelyn ap Gruffudd
Llywelyn ap Gruffudd was the 13th-century Prince of Wales and the last native ruler to unite much of Wales before its conquest by England.
-
C.
Madog ap Llywelyn
Madog ap Llywelyn was a Welsh nobleman who led a major revolt against English rule in Wales in 1294–1295, briefly styling himself Prince of Wales.
-
D.
Elis Gruffydd
Elis Gruffydd was a 16th-century Welsh soldier and chronicler best known for his extensive world chronicle written in the Welsh language.
-
E.
Llywelyn the Great
Llywelyn the Great was a 13th-century Prince of Gwynedd who became the most powerful Welsh ruler of his time, effectively uniting much of Wales under his leadership.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eeb81bf08190b0352137eb4a5763 |
completed | April 20, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:06 p.m.