Triple
T578282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canna |
E15003
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Lochaber |
E35881
|
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: Lochaber | Statement: [Canna, region, Lochaber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lochaber Context triple: [Canna, region, Lochaber]
-
A.
Lochaber
chosen
Lochaber is a region in the western Scottish Highlands known for its rugged landscapes, including Britain’s highest mountain, Ben Nevis.
-
B.
Tullibigeal
Tullibigeal is a small rural town in New South Wales, Australia, known for its agricultural community and location within the Riverina region.
-
C.
Seaforth
Seaforth is a coastal town in the parish of St. Thomas in eastern Jamaica, known for its rural setting and Caribbean shoreline.
-
D.
Aberfoyle
Aberfoyle is a village in the Stirling council area of Scotland, known as a gateway to the Trossachs and the Loch Lomond and The Trossachs National Park.
-
E.
Inchgarvie
Inchgarvie is a small rocky island in Scotland’s Firth of Forth, best known for its historic fortifications and its role in supporting the Forth Bridge.
- 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_69a4935783b8819082b77726ec10cc42 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49b69fed88190b5558d4ebd5047a1 |
completed | March 1, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a50e23bce481908404040b848ba9c1 |
completed | March 2, 2026, 4:12 a.m. |
Created at: March 1, 2026, 7:33 p.m.