Triple
T1291587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A90 road |
E27559
|
entity |
| Predicate | passesThrough |
P225
|
FINISHED |
| Object | Angus |
E2212
|
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: Angus | Statement: [A90 road, passesThrough, Angus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angus Context triple: [A90 road, passesThrough, Angus]
-
A.
Angus
chosen
Angus is a historic county and region on the east coast of Scotland known for its rural landscapes, agriculture, and coastal towns.
-
B.
Angus South
Angus South is a Scottish Parliament constituency covering part of the Angus council area, including the town of Carnoustie.
-
C.
Bassett
Bassett is the surname of acclaimed American actress and director Angela Bassett, known for her powerful performances in film and television.
-
D.
Landseer
Landseer is the middle name of renowned British architect Sir Edwin Lutyens, best known for his influential country houses and war memorial designs.
-
E.
Veluws
Veluws is a Dutch Low Saxon dialect spoken in the Veluwe region of the Netherlands, closely related to other eastern Dutch dialects such as Achterhooks.
- 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_69a496d4ec448190ad653b2590c46711 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c0d7d15081909d3af19b9297f1cc |
completed | March 1, 2026, 10:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acbae7182081908b7045a15a2275d8 |
completed | March 7, 2026, 11:55 p.m. |
Created at: March 1, 2026, 7:51 p.m.