Triple
T25169737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Landore Viaduct |
E630285
|
entity |
| Predicate | crossesAtLocation |
P27425
|
FINISHED |
| Object | River Tawe in Swansea |
—
|
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: River Tawe in Swansea | Statement: [Landore Viaduct, crossesAtLocation, River Tawe in Swansea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossesAtLocation Context triple: [Landore Viaduct, crossesAtLocation, River Tawe in Swansea]
-
A.
crossesNear
Indicates that one entity passes across the path or area of another entity at a location that is close to, but not directly intersecting, the other entity.
-
B.
crossesAtHeight
Indicates that one entity passes over another at a specified vertical distance or elevation.
-
C.
crossesBetween
Indicates that one entity passes from one side of a second entity to the other, traversing the space between two reference points or boundaries associated with that second entity.
-
D.
crossesIn
chosen
Indicates that one entity passes over or through the path, boundary, or area occupied by another entity, intersecting its space or trajectory.
-
E.
crossesTo
Indicates that one entity moves or extends from one side or area to another, passing over or through some boundary or intervening space.
- 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_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 12:19 p.m.