Triple
T10515447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speak No Evil |
E248017
|
entity |
| Predicate | photographer |
P12333
|
FINISHED |
| Object | Francis Wolff |
E523794
|
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: Francis Wolff | Statement: [Speak No Evil, photographer, Francis Wolff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Francis Wolff Context triple: [Speak No Evil, photographer, Francis Wolff]
-
A.
Francis Wolff
chosen
Francis Wolff was a German-born photographer and record producer best known for his iconic session photographs and co-running the influential jazz label Blue Note Records.
-
B.
Richard Brooks
Richard Brooks was an American film director and screenwriter known for adapting literary works into acclaimed films such as "Cat on a Hot Tin Roof" and "In Cold Blood."
-
C.
Tom Benedek
Tom Benedek is an American screenwriter best known for co-writing the science fiction film "Cocoon."
-
D.
Robert Rossen
Robert Rossen was an American film director and screenwriter best known for socially conscious dramas such as "All the King's Men" and "The Hustler."
-
E.
Franklin J. Schaffner
Franklin J. Schaffner was an American film and television director best known for acclaimed works such as "Patton," "Planet of the Apes," and "Papillon."
- 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_69d381c4aa948190942e1d803143fb0e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509cbacb08190a446c864b97823ad |
completed | April 7, 2026, 1:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d95e63561081909af8b2242e896bfe |
completed | April 10, 2026, 8:32 p.m. |
Created at: April 6, 2026, 12:27 p.m.