Triple
T1308382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chevrolet Equinox |
E27931
|
entity |
| Predicate | bodyConfiguration |
P27802
|
FINISHED |
| Object | unibody construction |
—
|
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: unibody construction | Statement: [Chevrolet Equinox, bodyConfiguration, unibody construction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyConfiguration Context triple: [Chevrolet Equinox, bodyConfiguration, unibody construction]
-
A.
bodyPattern
Indicates a recurring or characteristic configuration, arrangement, or sequence exhibited by a body or physical form.
-
B.
body
Indicates that one entity is the physical body or main corporeal form of another entity.
-
C.
publicBody
Indicates that an entity functions as a governmental or publicly controlled organization that performs public duties or services.
-
D.
supportsBody
Indicates that one entity physically or structurally holds up, bears the weight of, or provides foundational stability for another entity’s body.
-
E.
hostsBody
Indicates that one entity serves as the physical container or location in which another entity resides or is situated.
- F. None of above. chosen
Provenance (4 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_69a496d7d83481908f83085854e51328 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c15490a88190872c3d2698a8f9c9 |
completed | March 1, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69a4bee9e4a88190b22ab2ee831a23c9 |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4c15361c8819094b8171e780b5560 |
completed | March 1, 2026, 10:44 p.m. |
Created at: March 1, 2026, 7:51 p.m.