Triple
T788612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lochgelly |
E16859
|
entity |
| Predicate | hasPostTown |
P2711
|
FINISHED |
| Object | LOCHGELLY |
E16859
|
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: LOCHGELLY | Statement: [Lochgelly, hasPostTown, LOCHGELLY]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LOCHGELLY Context triple: [Lochgelly, hasPostTown, LOCHGELLY]
-
A.
Lochgelly
chosen
Lochgelly is a former coal-mining town in Fife, Scotland, situated between Lochgelly Loch and the larger towns of Dunfermline and Kirkcaldy.
-
B.
Molloy Deep
Molloy Deep is the deepest known part of the Arctic Ocean, located in the Fram Strait between Greenland and Svalbard.
-
C.
Loch Ness
Loch Ness is a large, deep freshwater lake in the Scottish Highlands, world-famous for the legendary Loch Ness Monster said to inhabit its waters.
-
D.
Tullibigeal
Tullibigeal is a small rural town in New South Wales, Australia, known for its agricultural community and location within the Riverina region.
-
E.
Cairnryan
Cairnryan is a small Scottish coastal village best known as a major ferry port linking Scotland with Northern Ireland across the Irish Sea.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a782fe988190966b958673fe12bf |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a6787eac608190acc40d56f827284e |
completed | March 3, 2026, 5:58 a.m. |
Created at: March 1, 2026, 7:38 p.m.