Triple
T3066277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Beauty |
E62110
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Bruce Cohen |
E102051
|
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: Bruce Cohen | Statement: [American Beauty, producer, Bruce Cohen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bruce Cohen Context triple: [American Beauty, producer, Bruce Cohen]
-
A.
Bruce Cohen
chosen
Bruce Cohen is an American film and television producer best known for his work on acclaimed films such as "American Beauty" and "Silver Linings Playbook."
-
B.
Andrew Cohen
Andrew Cohen is an entrepreneur best known as a founder of the wireless technology company Qualcomm.
-
C.
Rob Cohen
Rob Cohen is an American film director and producer best known for helming high-profile action and adventure movies such as "The Fast and the Furious" and "xXx."
-
D.
Adam Cohen
Adam Cohen is a Canadian singer-songwriter and musician, best known as the son of legendary artist Leonard Cohen and for his own solo and band projects.
-
E.
Jake Cohen
Jake Cohen is known primarily as the son of Michael Cohen, the former personal attorney to Donald Trump.
- 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_69ad85793e5c8190a358049bc4a98d8c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada0fd87308190918e7b616f033faa |
completed | March 8, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1ef16cf2881908265dfe8a1e3424d |
completed | March 11, 2026, 10:39 p.m. |
Created at: March 8, 2026, 3:02 p.m.