Triple
T650272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Air Force roundel |
E11330
|
entity |
| Predicate | visualContrastFunction |
P16366
|
FINISHED |
| Object | aircraft identification |
—
|
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: aircraft identification | Statement: [French Air Force roundel, visualContrastFunction, aircraft identification]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualContrastFunction Context triple: [French Air Force roundel, visualContrastFunction, aircraft identification]
-
A.
themeContrast
Indicates a relationship where two themes are compared or opposed to highlight their differences or tension.
-
B.
visualEffect
chosen
Indicates that one entity produces, modifies, or is associated with a particular visual effect on another entity or within a scene.
-
C.
hasPerceptualQuality
Indicates that something possesses a particular sensory or perceptual characteristic, such as a color, sound, texture, taste, or smell.
-
D.
designLuminosity
Indicates the specified luminosity level or brightness characteristics that something is designed or intended to have.
-
E.
visualForm
Indicates the visual appearance, shape, or structural pattern that characterizes how something looks.
- 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f31e70c81909a2ac1d939f7ec07 |
completed | March 1, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69a49d0eade081909c47e85ed55f808d |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.