Triple
T23176315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GM New Look bus |
E579014
|
entity |
| Predicate | windshieldType |
P104024
|
FINISHED |
| Object | curved five-piece "fishbowl" windshield |
—
|
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: curved five-piece "fishbowl" windshield | Statement: [GM New Look bus, windshieldType, curved five-piece "fishbowl" windshield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windshieldType Context triple: [GM New Look bus, windshieldType, curved five-piece "fishbowl" windshield]
-
A.
windscreen
Indicates that one entity serves as the windscreen (protective transparent barrier, typically at the front of a vehicle or device) for another entity.
-
B.
hasWindScreens
Indicates that an entity is equipped with or features wind screens, which serve as barriers or shields against wind.
-
C.
glazingType
Indicates the type or configuration of glazing (such as single, double, or special coatings) used in or applied to an element.
-
D.
windowMaterial
Indicates the material from which a window is made or constructed.
-
E.
glassType
chosen
Indicates the specific kind or category of glass associated with or used by an entity.
- 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_69e245fd2a388190b814c0dfa15f7148 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f6a8644819099b107bb13ea16ff |
completed | April 29, 2026, 4:56 a.m. |
| PD | Predicate disambiguation | batch_69ef8a041c0081909afb670d17a5aaba |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:04 p.m.