Triple
T22756582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peugeot 9X8 |
E562858
|
entity |
| Predicate | liveryTheme |
P17744
|
FINISHED |
| Object | Peugeot lion claw light motifs |
—
|
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: Peugeot lion claw light motifs | Statement: [Peugeot 9X8, liveryTheme, Peugeot lion claw light motifs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: liveryTheme Context triple: [Peugeot 9X8, liveryTheme, Peugeot lion claw light motifs]
-
A.
liveryColors
Indicates the specific set of colors used as the official or characteristic color scheme associated with an entity (such as a brand, organization, or vehicle).
-
B.
liveryFeature
chosen
Indicates a characteristic or design element that is part of a specific livery or external appearance scheme.
-
C.
liveryInspiredBy
Indicates that one livery’s design, colors, or overall appearance is based on, influenced by, or pays homage to another livery.
-
D.
hasLivery
Indicates that one entity bears or displays the distinctive colors, markings, or branding (livery) associated with another entity.
-
E.
vehicleTheme
Indicates that an entity serves as the vehicle or means through which another entity, event, or action is carried out or expressed.
- 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_69e24551ec7881909a9c924dbea155f6 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f179bd22588190ac724a656194f5b9 |
completed | April 29, 2026, 3:23 a.m. |
| PD | Predicate disambiguation | batch_69eed2b88d88819096015deb6a648801 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:25 p.m.