Triple
T25170408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Tyne (East Lothian) |
E630306
|
entity |
| Predicate | mouthNearSettlement |
P18935
|
FINISHED |
| Object | Dunbar |
—
|
NE NERFINISHED |
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: Dunbar | Statement: [River Tyne (East Lothian), mouthNearSettlement, Dunbar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mouthNearSettlement Context triple: [River Tyne (East Lothian), mouthNearSettlement, Dunbar]
-
A.
mouthLocatedInAdministrativeEntity
Indicates that the place where a river ends (its mouth) is situated within a specific administrative region or jurisdiction.
-
B.
mouthNear
chosen
Indicates that one entity’s mouth is positioned close to another entity or object in space.
-
C.
mouthOf
Indicates the location where one entity (typically a river or similar feature) empties into or opens out into another, larger body or feature.
-
D.
hasMouthPositionRelativeToCity
Indicates the spatial position of a river’s mouth in relation to a specified city.
-
E.
mouthState
Indicates the current condition or configuration of an entity’s mouth, such as whether it is open, closed, or in another specific state.
- F. None of above.
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_69e75a87c9b88190ab60731902a99750 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46d467e6c8190a328ee6b07aef240 |
completed | May 1, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:20 p.m.