Triple
T2117007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary McCartney |
E43831
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | portrait photographer |
C8216
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: portrait photographer Context triple: [Mary McCartney, instanceOf, portrait photographer]
-
A.
aerial photographer
An aerial photographer is a professional who captures images or video from elevated positions—such as drones, aircraft, or tall structures—to document landscapes, structures, events, or geographic data from a bird’s-eye view.
-
B.
wildlife photographer
A wildlife photographer is a professional or enthusiast who specializes in capturing images of animals and natural environments in their native habitats, often requiring patience, fieldcraft, and knowledge of animal behavior.
-
C.
cinematographer
A cinematographer is the visual storyteller responsible for crafting a film’s look through camera work, lighting, and shot composition in collaboration with the director.
-
D.
fashion model
A fashion model is a professional who showcases clothing, accessories, and styles for designers, brands, and media through runway shows, photo shoots, and promotional appearances.
-
E.
Magnum Photos member
A Magnum Photos member is a distinguished photographer elected into the Magnum Photos cooperative, recognized for their exceptional documentary and artistic work and granted shared ownership and decision-making within the agency.
- F. None of above. chosen
Provenance (1 batch)
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_69a88717cfe48190b7ecdd68c824848a |
completed | March 4, 2026, 7:25 p.m. |
Created at: March 4, 2026, 7:43 p.m.