Triple
T29789698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grace Jones "Island Life" cover |
E756367
|
entity |
| Predicate | featuresPose |
P15582
|
FINISHED |
| Object | impossible contorted pose |
—
|
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: impossible contorted pose | Statement: [Grace Jones "Island Life" cover, featuresPose, impossible contorted pose]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresPose Context triple: [Grace Jones "Island Life" cover, featuresPose, impossible contorted pose]
-
A.
featuresPosition
Indicates that one entity specifies or defines the spatial or ordered position of another entity.
-
B.
featuresRepresentationOf
Indicates that one entity visually or symbolically depicts, portrays, or includes a representation of another entity.
-
C.
showsPose
chosen
Indicates that one entity displays or presents a particular pose or bodily posture of another entity.
-
D.
featuresSceneFrom
Indicates that one entity (such as a work or media item) includes or presents a particular scene taken from another entity.
-
E.
featuresPerspective
Indicates that one entity presents, embodies, or incorporates the viewpoint, angle, or outlook provided by another entity.
- 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_69f22451fb748190bbdbab401280affb |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69ff9d9cb4f8819083682be3c483b599 |
completed | May 9, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69ff9c38bf9c8190bbb85b32f3ae3d2e |
completed | May 9, 2026, 8:42 p.m. |
Created at: April 29, 2026, 5:11 p.m.