Triple
T12188222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breda LRV2 |
E290391
|
entity |
| Predicate | railwaySignallingType |
P40340
|
FINISHED |
| Object | light rail |
—
|
LITERAL 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: light rail | Statement: [Breda LRV2, railwaySignallingType, light rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwaySignallingType Context triple: [Breda LRV2, railwaySignallingType, light rail]
-
A.
usesRailwaySignallingSystem
chosen
Indicates that one entity operates or applies a particular railway signalling system in the context of train or rail traffic control.
-
B.
railwaySign
Indicates that one entity functions as a railway-related sign or signal that conveys information or instructions within a rail transport context to another entity.
-
C.
railSystemType
Indicates the specific category or classification of a rail transportation system that an entity belongs to or operates within.
-
D.
railwayLineType
Indicates the specific kind or classification of a railway line associated with an entity (e.g., main line, branch line, high-speed line).
-
E.
signallingSystem
Indicates that one entity functions as a signalling system used to transmit information or cues to another entity.
- 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_69d6ab64de5881908d56eb7a75c6cc69 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91a83012c81908d04bbab5fdcd8c2 |
completed | April 10, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_69d91510a258819090ef8fbdc2d8707b |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.