Triple
T15438105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady in a Green Jacket |
E369821
|
entity |
| Predicate | usesColorContrast |
P43203
|
FINISHED |
| Object | vibrant color contrasts |
—
|
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: vibrant color contrasts | Statement: [Lady in a Green Jacket, usesColorContrast, vibrant color contrasts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesColorContrast Context triple: [Lady in a Green Jacket, usesColorContrast, vibrant color contrasts]
-
A.
hasTeamColorContrast
Indicates that there is a sufficient visual contrast between the colors associated with a team and another relevant color set (such as opponents, background, or interface elements).
-
B.
contrastRatio
chosen
Indicates the proportional difference in luminance or intensity between two visual elements being compared.
-
C.
hasMainContrast
Indicates a primary opposing or differing relationship between two elements, highlighting the main point of contrast between them.
-
D.
themeContrast
Indicates a relationship where two themes are compared or opposed to highlight their differences or tension.
-
E.
registerContrast
Indicates that an entity records or establishes a distinction or difference between two or more items or states.
- 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_69d85a19180081909925012fbf4e62a3 |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03edca064819081510bf303271062 |
completed | April 16, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69ded28276f481908c2038bb301e57cf |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:21 a.m.