Triple
T23196027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail second-generation DMUs |
E579870
|
entity |
| Predicate | traction type |
P19787
|
FINISHED |
| Object | diesel-mechanical |
—
|
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: diesel-mechanical | Statement: [British Rail second-generation DMUs, traction type, diesel-mechanical]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traction type Context triple: [British Rail second-generation DMUs, traction type, diesel-mechanical]
-
A.
tractionType
chosen
Indicates the type or method of traction applied or used in relation to an entity or system.
-
B.
traction
Indicates the degree to which one entity’s movement or influence effectively grips, pulls, or gains momentum relative to another entity or medium.
-
C.
strainType
Indicates the specific variety or subtype classification within a broader category of strains (e.g., biological, chemical, or product strains).
-
D.
tractionControl
Indicates that a system regulates wheel slip to maintain optimal traction between a vehicle’s tires and the driving surface.
-
E.
lapType
Indicates the specific category or kind of lap being performed or recorded within an activity or event.
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fdb279c81908dcc46f2786a86cd |
completed | April 29, 2026, 4:58 a.m. |
| PD | Predicate disambiguation | batch_69ef8a041c0081909afb670d17a5aaba |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:06 p.m.