Triple
T8155845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Florence Foster Jenkins |
E190447
|
entity |
| Predicate | cinematographer |
P1953
|
FINISHED |
| Object | Danny Cohen |
E33367
|
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: Danny Cohen | Statement: [Florence Foster Jenkins, cinematographer, Danny Cohen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Danny Cohen Context triple: [Florence Foster Jenkins, cinematographer, Danny Cohen]
-
A.
Danny Cohen
chosen
Danny Cohen is a British cinematographer known for his acclaimed work on films such as The King’s Speech and collaborations with director Tom Hooper.
-
B.
Dan Cohen
Dan Cohen is a film and television producer best known for his work on major genre projects, including serving as an executive producer on the hit Netflix series "Stranger Things."
-
C.
Jon Cohen
Jon Cohen is a screenwriter best known for co-writing the science fiction film "Minority Report."
-
D.
Peter Cohen
Peter Cohen is a musician best known as a member of the South African Afro-fusion band Freshlyground.
-
E.
Andrew Cohen
Andrew Cohen is an entrepreneur best known as a founder of the wireless technology company Qualcomm.
- 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_69ca82bfeb6481909d07b91b5cf69f59 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb44d8a37481909397b5cc321b94be |
completed | March 31, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf0f68c88190be9aab03de6bf4a0 |
completed | April 1, 2026, 6:45 a.m. |
Created at: March 30, 2026, 5:37 p.m.