Triple
T623923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vivian "Buster" Burey Marshall |
E14572
|
entity |
| Predicate | mediaDepictionAs |
P17824
|
FINISHED |
| Object | unsung hero of civil rights movement |
—
|
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: unsung hero of civil rights movement | Statement: [Vivian "Buster" Burey Marshall, mediaDepictionAs, unsung hero of civil rights movement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediaDepictionAs Context triple: [Vivian "Buster" Burey Marshall, mediaDepictionAs, unsung hero of civil rights movement]
-
A.
mediaAspect
Indicates the specific aspect ratio or dimensional proportion of a media item in relation to its width and height.
-
B.
depictsMedium
Indicates that one entity visually represents or portrays the medium or material of another entity.
-
C.
mediaOrigin
Indicates the original source or provenance from which a piece of media (such as an image, video, or audio) was derived or obtained.
-
D.
culturalDepictionBy
Indicates that one entity serves as the creator or source of a cultural representation or portrayal of another entity.
-
E.
depictionType
Indicates the specific manner or style in which something is visually represented or depicted.
- F. None of above. chosen
Provenance (4 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e41753881909f0faed720cc31bc |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49d0069d0819087c83b608f6fc053 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49e2107548190af0c1d67cfa475d1 |
completed | March 1, 2026, 8:14 p.m. |
Created at: March 1, 2026, 7:35 p.m.