Triple
T8717206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jewel Box cluster |
E206924
|
entity |
| Predicate | hasColorContrastDescribedAs |
P48842
|
FINISHED |
| Object | a casket of variously colored precious stones |
—
|
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: a casket of variously colored precious stones | Statement: [Jewel Box cluster, hasColorContrastDescribedAs, a casket of variously colored precious stones]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColorContrastDescribedAs Context triple: [Jewel Box cluster, hasColorContrastDescribedAs, a casket of variously colored precious stones]
-
A.
contrastRatio
Indicates the proportional difference in luminance or intensity between two visual elements being compared.
-
B.
hasMainContrast
Indicates a primary opposing or differing relationship between two elements, highlighting the main point of contrast between them.
-
C.
hasComplementaryColor
Indicates that one color is the complementary (i.e., opposite on the color wheel, providing maximum contrast) counterpart of another color.
-
D.
hasColorInfo
chosen
Indicates that an entity is associated with specific color-related information or attributes.
-
E.
hasDensityContrast
Indicates that one entity differs from another in material density, highlighting a contrast in how compact or dense they are.
- 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_69ca83572d4881909bef3be2b578d539 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5cd9c2a08190a65ab0ce573153d2 |
completed | March 31, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69cc456e806c819087e7d66ee737f242 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:36 p.m.