Triple
T3740178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GMC Savana van platform |
E79678
|
entity |
| Predicate | supportsUpfitting |
P42045
|
FINISHED |
| Object | emergency services vehicles |
—
|
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: emergency services vehicles | Statement: [GMC Savana van platform, supportsUpfitting, emergency services vehicles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsUpfitting Context triple: [GMC Savana van platform, supportsUpfitting, emergency services vehicles]
-
A.
supportsProduct
Indicates that one entity provides assistance, compatibility, or necessary resources for the operation, use, or maintenance of a specified product.
-
B.
isSuitableFor
Indicates that one entity is appropriate, fitting, or well-matched for use, application, or association with another entity.
-
C.
usesSupportItem
Indicates that an entity employs or relies on a supporting item, tool, or aid to perform an action or fulfill a function.
-
D.
supportsInstallation
Indicates that one entity is capable of enabling, handling, or being compatible with the installation of another entity.
-
E.
supportsBodyType
chosen
Indicates that one entity is compatible with, designed for, or can accommodate a specified body 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_69ad8b115610819095b02007da5ca3cb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb5344fc8190b183aca5c04e3bcc |
completed | March 8, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69adc048f28c819092bed16a95a3cac1 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.