Triple
T19490588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nash Point Lighthouse |
E487636
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | St Donats |
—
|
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: St Donats | Statement: [Nash Point Lighthouse, near, St Donats]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: St Donats Context triple: [Nash Point Lighthouse, near, St Donats]
-
A.
St Donats
chosen
St Donats is a coastal village in the Vale of Glamorgan, Wales, best known for its historic St Donat’s Castle and association with Atlantic College.
-
B.
Mister Donut
Mister Donut is an international doughnut and coffee shop chain, originally founded in the United States and now best known for its widespread presence and popularity in Japan and parts of Asia.
-
C.
Godiva
Godiva is the legendary Anglo-Saxon noblewoman famed for riding naked through the streets of Coventry to protest her husband's oppressive taxation of his tenants.
-
D.
Carvel
Carvel is a fictional small American town that serves as the primary setting for the Andy Hardy film series.
-
E.
Voodoo Doughnut
Voodoo Doughnut is a quirky, Portland-born doughnut shop chain famous for its creative, over-the-top doughnuts and eclectic atmosphere.
- 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6348d43448190bf83680522b8b415 |
completed | April 20, 2026, 2:13 p.m. |
Created at: April 10, 2026, 1:39 p.m.