Triple
T26080186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Bradley |
E657813
|
entity |
| Predicate | photographDepictedIn |
P92892
|
FINISHED |
| Object | Raising the Flag on Iwo Jima |
—
|
NE NERFINISHED |
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: Raising the Flag on Iwo Jima | Statement: [John Bradley, photographDepictedIn, Raising the Flag on Iwo Jima]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: photographDepictedIn Context triple: [John Bradley, photographDepictedIn, Raising the Flag on Iwo Jima]
-
A.
imageDepictedIn
chosen
Indicates that a particular image is shown, represented, or included within another resource or context.
-
B.
commonlyDepictedOn
Indicates that something is frequently shown or represented on the surface, medium, or context of another thing.
-
C.
picturisedOn
Indicates that something (such as a scene, story, or work) has been visually depicted or represented based on a particular subject, source, or reference.
-
D.
depictsAuthorOf
Indicates that one entity visually represents or portrays the person who is the author of another entity.
-
E.
isDepictedVia
Indicates that one entity is represented, illustrated, or shown by means of another entity, such as a specific medium, style, or method of depiction.
- 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_69ee5bbf0d208190801ee95d4f07fb16 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f606f9ef608190b1e7f2c179761cd8 |
completed | May 2, 2026, 2:15 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 7:37 p.m.