Triple
T7914798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martha McMillan Roberts |
E183792
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Farm Security Administration photographer |
C8374
|
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: Farm Security Administration photographer Context triple: [Martha McMillan Roberts, instanceOf, Farm Security Administration photographer]
-
A.
American photographer
chosen
An American photographer is a visual artist from the United States who uses photographic techniques to capture, interpret, and communicate subjects, stories, or concepts through images.
-
B.
New Deal art project
A New Deal art project is a government-funded initiative from the 1930s that employed artists to create public artworks—such as murals, sculptures, and posters—as part of broader economic relief and cultural enrichment efforts.
-
C.
government photography project
A government photography project is an organized initiative, typically funded and directed by a public agency, that commissions or collects photographic work to document, promote, or analyze specific social, cultural, environmental, or historical subjects in support of public policy or archival goals.
-
D.
documentary photographer
A documentary photographer is a visual storyteller who uses candid, real-world images to truthfully record events, environments, and social conditions over time.
-
E.
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.
- F. None of above.
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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
Created at: March 30, 2026, 5:05 p.m.