Triple
T7839307
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don McCullin |
E181764
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Don McCullin |
E181764
|
NE 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: Don McCullin | Statement: [Don McCullin, name, Don McCullin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don McCullin Context triple: [Don McCullin, name, Don McCullin]
-
A.
Don McCullin
chosen
Don McCullin is a renowned British photojournalist celebrated for his powerful and often harrowing images of war, conflict, and social hardship around the world.
-
B.
Philip Jones Griffiths
Philip Jones Griffiths was a renowned Welsh photojournalist best known for his powerful and critical coverage of the Vietnam War.
-
C.
W. Eugene Smith
W. Eugene Smith was a pioneering American photojournalist renowned for his powerful, humanistic photo-essays in magazines like Life.
-
D.
Elliott Erwitt
Elliott Erwitt was a renowned American photographer celebrated for his candid black-and-white images that blend street photography with subtle humor and humanism.
-
E.
James Nachtwey
James Nachtwey is an acclaimed American photojournalist renowned for his powerful war and conflict photography documenting human suffering around the world.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8284a25c8190a1a20afad30da792 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb14c4680481908628d22bbe4842f4 |
completed | March 31, 2026, 12:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5abff2a88190a2f988b8b041ebb0 |
completed | March 31, 2026, 5:25 a.m. |
Created at: March 30, 2026, 4:47 p.m.