Triple
T22399291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Hams |
E553714
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Tor Bay |
—
|
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: Tor Bay | Statement: [South Hams, locatedNear, Tor Bay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tor Bay Context triple: [South Hams, locatedNear, Tor Bay]
-
A.
Tor Bay
chosen
Tor Bay is a coastal bay in Devon, England, known for its sheltered waters, seaside towns, and maritime activities.
-
B.
Pot Bay
Pot Bay is the English translation of the Norwegian name "Grytviken," a historic whaling station settlement on the sub-Antarctic island of South Georgia.
-
C.
Gills Bay
Gills Bay is a small coastal settlement in Caithness, northern Scotland, known as a mainland ferry terminal for services to the Orkney Islands.
-
D.
Carlyon Bay
Carlyon Bay is a coastal area in Cornwall, England, known for its sandy beaches, dramatic cliffs, and seaside resort amenities.
-
E.
Totland Bay
Totland Bay is a scenic coastal bay and beach on the western side of the Isle of Wight in England, known for its views across the Solent and Victorian-era pier.
- 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158b28e58819090624f131ce63a9f |
completed | April 29, 2026, 1:02 a.m. |
Created at: April 16, 2026, 8:46 p.m.