Triple
T505261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Watt |
E10488
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Greenock |
E27634
|
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: Greenock | Statement: [James Watt, residence, Greenock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greenock Context triple: [James Watt, residence, Greenock]
-
A.
Greenock
chosen
Greenock is a historic port town and former shipbuilding center on the River Clyde in western Scotland.
-
B.
Gourock
Gourock is a coastal town and ferry port on the Firth of Clyde in Inverclyde, western Scotland.
-
C.
Kilmarnock
Kilmarnock is a large town in East Ayrshire, Scotland, historically known for its textile and engineering industries and its association with the poet Robert Burns.
-
D.
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.
-
E.
Inverness
Inverness is a city in the Scottish Highlands that serves as a major cultural and administrative center for the region.
- 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_69a2e848adf881908e5e04f7af030093 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f14b2acc8190818e8a53eac69c54 |
completed | Feb. 28, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac1185da8c8190a70f4fd885bbe209 |
completed | March 7, 2026, 11:52 a.m. |
Created at: Feb. 28, 2026, 1:12 p.m.