Triple
T31091313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CRH380D |
E792393
|
entity |
| Predicate | hasTraction |
P132066
|
FINISHED |
| Object | distributed traction |
—
|
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: distributed traction | Statement: [CRH380D, hasTraction, distributed traction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTraction Context triple: [CRH380D, hasTraction, distributed traction]
-
A.
usedTractionType
Indicates the type of traction or drive mechanism that was employed in performing the action or operating the entity.
-
B.
typicalTractionType
chosen
Indicates the usual or most common type of traction mechanism associated with an entity (such as how it is typically powered or driven).
-
C.
currentTractionType
Indicates the type or mode of traction currently being applied or in use in a given context.
-
D.
hasRailwayTraction
Indicates that a railway system, line, or vehicle uses a specified type or method of traction (e.g., electric, diesel, steam) for its propulsion.
-
E.
secondaryTractionType
Indicates the additional or backup type of traction or propulsion method associated with an entity, complementing its primary traction type.
- 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_69f224ce48348190bd0fc23f656ed683 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: April 29, 2026, 9:02 p.m.