Triple
T9214789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Images à la sauvette |
E221214
|
entity |
| Predicate | photographicStyle |
P62927
|
FINISHED |
| Object | candid photography |
—
|
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: candid photography | Statement: [Images à la sauvette, photographicStyle, candid photography]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: photographicStyle Context triple: [Images à la sauvette, photographicStyle, candid photography]
-
A.
artisticStyle
Indicates the artistic movement, style, or aesthetic approach that characterizes how something is created or visually expressed.
-
B.
photographyGenre
chosen
Indicates the specific genre or style of photography that characterizes a photographic work or activity.
-
C.
cameraStyle
Indicates the characteristic visual approach or technique used by a camera in capturing or presenting imagery.
-
D.
isPhotographicSubject
Indicates that an entity serves as the subject or main focus captured in a photograph taken by another entity.
-
E.
hasFilmStyle
Indicates that a film exhibits or is characterized by a particular cinematic style or aesthetic approach.
- 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda0830a8819096a186ed2e976cba |
completed | April 1, 2026, 8:40 a.m. |
| PD | Predicate disambiguation | batch_69cc660ce23c81909c7bbe10f4a05f36 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:27 p.m.