Triple
T25826712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunting Stewart tartan |
E650549
|
entity |
| Predicate | contrastProperty |
P148155
|
FINISHED |
| Object | Hunting Stewart is darker and more muted |
—
|
NE NERFINISHED |
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: Hunting Stewart is darker and more muted | Statement: [Hunting Stewart tartan, contrastProperty, Hunting Stewart is darker and more muted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contrastProperty Context triple: [Hunting Stewart tartan, contrastProperty, Hunting Stewart is darker and more muted]
-
A.
contrastUse
Indicates that one entity is used in opposition or distinction to another to highlight differences between them.
-
B.
contrastCharacteristic
Indicates that two entities are being compared by highlighting opposing or significantly different characteristics between them.
-
C.
contrastGoal
Indicates a relationship where one goal is defined in opposition to, or as a contrasting alternative to, another goal.
-
D.
contrastEffect
Indicates that one entity’s characteristics are perceived or evaluated differently because they are compared or juxtaposed with another entity.
-
E.
contrastLevel
chosen
Indicates the degree of visual or perceptual difference between two elements, such as brightness, color, or intensity, within a given context.
- 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_69e7ab37438081908f1ccf6284839520 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 22, 2026, 7:36 a.m.