Triple
T20717141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cowal Peninsula |
E509200
|
entity |
| Predicate | hasVillage |
P4011
|
FINISHED |
| Object | Sandbank |
—
|
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: Sandbank | Statement: [Cowal Peninsula, hasVillage, Sandbank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandbank Context triple: [Cowal Peninsula, hasVillage, Sandbank]
-
A.
Sandbank
chosen
Sandbank is a small coastal village on the Cowal peninsula in Argyll and Bute, western Scotland.
-
B.
Sandbanks
Sandbanks is an exclusive, affluent coastal peninsula in Dorset, England, renowned for its sandy beaches and some of the most expensive real estate in the UK.
-
C.
Miriam Sandbank
Miriam Sandbank is best known as the wife of renowned conductor Lorin Maazel.
-
D.
Whiteford Sands
Whiteford Sands is a remote, expansive sandy beach on the Gower Peninsula in South Wales, known for its unspoiled dunes, wildlife, and the cast-iron Whiteford Lighthouse.
-
E.
Blacktoft Sands
Blacktoft Sands is a renowned RSPB nature reserve on the Humber Estuary in East Yorkshire, England, famous for its wetland habitats and diverse birdlife.
- 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d2c57481909840945ffd3b0cc3 |
completed | April 21, 2026, 12:16 a.m. |
Created at: April 16, 2026, 12:16 p.m.