Triple
T1140315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bombardier Voyager family |
E23434
|
entity |
| Predicate | brakingSystem |
P4166
|
FINISHED |
| Object | electro-pneumatic brakes |
—
|
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: electro-pneumatic brakes | Statement: [Bombardier Voyager family, brakingSystem, electro-pneumatic brakes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brakingSystem Context triple: [Bombardier Voyager family, brakingSystem, electro-pneumatic brakes]
-
A.
brakeType
chosen
Indicates the specific kind or system of brakes associated with an entity.
-
B.
suspensionType
Indicates the specific kind or configuration of suspension system associated with an entity (e.g., a vehicle or structure).
-
C.
chassis
Indicates that one entity serves as the structural frame or supporting base (chassis) for another entity.
-
D.
chassisMaterialFeature
Indicates that an entity has a chassis characterized by a specific material-related feature or property.
-
E.
suspension
Indicates the temporary removal or halting of a privilege, activity, or status for an entity, often as a consequence or precaution.
- 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_69a493ef399c8190b04b9146d2314f59 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bde18d208190848c189b2b8d585f |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4b52d48190bec2e7ad1cc8efc0 |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.