Triple
T2916834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cardross |
E78626
|
entity |
| Predicate | hasPostTown |
P2711
|
FINISHED |
| Object | Dumbarton |
E214623
|
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: Dumbarton | Statement: [Cardross, hasPostTown, Dumbarton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dumbarton Context triple: [Cardross, hasPostTown, Dumbarton]
-
A.
Dumbarton
chosen
Dumbarton is a historic Scottish town on the River Clyde known for its prominent role in shipbuilding and maritime industry.
-
B.
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.
-
C.
Clydebank
Clydebank is a Scottish town on the River Clyde that was heavily industrialized and became notorious for the devastating air raids it suffered during the Second World War.
-
D.
Alberton
Alberton is a town in the East Rand region of Gauteng, South Africa, forming part of the greater Johannesburg metropolitan area.
-
E.
Alloa
Alloa is a town in central Scotland that serves as the main commercial and population hub of Clackmannanshire.
- 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_69ad8b0c2ad081909ff87050ae542bb9 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad96a2bdd88190aa01c26a27f9afbd |
completed | March 8, 2026, 3:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b0866113688190ae222813b017c69f |
completed | March 10, 2026, 9 p.m. |
Created at: March 8, 2026, 2:53 p.m.