Triple
T16988039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glenfinnan railway station |
E412120
|
entity |
| Predicate | between |
P1262
|
FINISHED |
| Object | Mallaig |
E76807
|
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: Mallaig | Statement: [Glenfinnan railway station, between, Mallaig]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mallaig Context triple: [Glenfinnan railway station, between, Mallaig]
-
A.
Mallaig
chosen
Mallaig is a small fishing port and ferry terminal on the west coast of the Scottish Highlands, serving as a key gateway to the Inner Hebrides.
-
B.
Airmagh
Airmagh is the Ulster Scots name for the city of Armagh in Northern Ireland, known for its religious and historical significance.
-
C.
Maffra
Maffra is a small rural locality in the Snowy Monaro region of New South Wales, Australia.
-
D.
Kilmallock
Kilmallock is a historic market town in County Limerick, Ireland, known for its medieval walls, ecclesiastical ruins, and significant role in Irish history.
-
E.
Ballygrant
Ballygrant is a small rural village on the Scottish island of Islay, known for its traditional community and scenic Hebridean surroundings.
- 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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d27cd2048190800a60ae653e11e1 |
completed | April 18, 2026, 6:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc12e308819093e7f8933cdd6ba9 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:32 a.m.