Triple
T562604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cramond Island |
E13485
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Cramond |
E34955
|
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: Cramond | Statement: [Cramond Island, locatedNear, Cramond]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cramond Context triple: [Cramond Island, locatedNear, Cramond]
-
A.
Aberdour
Aberdour is a coastal village in Fife, Scotland, known for its historic castle, scenic beaches, and role as a commuter stop between Edinburgh and the Fife region.
-
B.
Inverkeithing
Inverkeithing is a coastal town in Fife, Scotland, situated near the Forth bridges and functioning as a key commuter hub for the Edinburgh area.
-
C.
Helensburgh
Helensburgh is a coastal town in Argyll and Bute, Scotland, situated on the north shore of the Firth of Clyde and known for its Victorian architecture and seaside setting.
-
D.
Leith
chosen
Leith is a historic port district of Edinburgh, Scotland, known for its maritime heritage and revitalized waterfront.
-
E.
Kirkcaldy
Kirkcaldy is a coastal town on the east coast of Scotland, known historically for its linoleum industry and as one of the largest settlements in Fife.
- 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_69a4933edcf08190b35ecfd6014caee6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49a700e608190b235246df057bd9b |
completed | March 1, 2026, 7:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac2a03fc748190b14d8fe066902c97 |
completed | March 7, 2026, 1:37 p.m. |
Created at: March 1, 2026, 7:32 p.m.