Triple
T13455549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westinghouse H2C |
E311221
|
entity |
| Predicate | usedOnCarClass |
P97747
|
FINISHED |
| Object | R46 |
—
|
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: R46 | Statement: [Westinghouse H2C, usedOnCarClass, R46]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedOnCarClass Context triple: [Westinghouse H2C, usedOnCarClass, R46]
-
A.
automotiveClassSupported
Indicates that a particular automotive class or category is supported or compatible within a given context or system.
-
B.
appliedToVehicleType
Indicates that something (such as a rule, restriction, or condition) is specifically applicable to a particular type or category of vehicle.
-
C.
intendedVehicleClass
chosen
Indicates that one entity is designed or specified to be used with, or is appropriate for, a particular class or category of vehicle.
-
D.
usedOnBrand
Indicates that something (such as a product, material, or element) is applied to, associated with, or utilized in connection with a particular brand.
-
E.
usedOnPart
Indicates that something is applied to, operates on, or is intended for use with a specific part of a larger object or system.
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaefc52448190b30d7999f44a9765 |
completed | April 12, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69d9a03ce03481908c61094f0cc0c158 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:41 p.m.