Triple
T9780314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scarlett Johansson as Silken Floss |
E237349
|
entity |
| Predicate | visualStyleOfWork |
P61564
|
FINISHED |
| Object | stylized comic-book aesthetic |
—
|
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: stylized comic-book aesthetic | Statement: [Scarlett Johansson as Silken Floss, visualStyleOfWork, stylized comic-book aesthetic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualStyleOfWork Context triple: [Scarlett Johansson as Silken Floss, visualStyleOfWork, stylized comic-book aesthetic]
-
A.
structuralStyle
Indicates the architectural or design style that characterizes the structure or form of an entity.
-
B.
studioOfWork
Indicates that a particular studio is the place where a given work (such as a film, artwork, or recording) was created, produced, or primarily developed.
-
C.
notableWorkStyle
Indicates a stylistic characteristic or distinctive manner associated with a notable work created by the subject.
-
D.
typicalVisualStyle
chosen
Indicates the characteristic or commonly observed visual appearance or aesthetic style associated with an entity.
-
E.
hasWorkStyle
Indicates the type or manner in which an entity typically performs work or carries out tasks.
- 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_69ca84d975a08190aab25b02a89bdab3 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda1b0b15881909ef52d0156148c59 |
completed | April 1, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69cd03d77c6c81909b675955bf113320 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:27 p.m.