Triple
T9015391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duplicity |
E215581
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Kerry Orent |
E387032
|
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: Kerry Orent | Statement: [Duplicity, producer, Kerry Orent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kerry Orent Context triple: [Duplicity, producer, Kerry Orent]
-
A.
Kerry Orent
chosen
Kerry Orent is a film producer known for his work on acclaimed movies such as "Michael Clayton."
-
B.
Jody Gerson
Jody Gerson is a prominent American music executive and producer, best known as the CEO and Chairman of Universal Music Publishing Group.
-
C.
Leslie Kogan
Leslie Kogan is the wife of American singer-songwriter Andrew Gold, known for her connection to the acclaimed musician behind hits like "Lonely Boy" and "Thank You for Being a Friend."
-
D.
Leslie Greif
Leslie Greif is an American television producer and director best known for creating and producing popular series and miniseries across action, drama, and true-crime genres.
-
E.
Jo Eisinger
Jo Eisinger was an American screenwriter best known for his dark, psychologically complex film noir scripts, including classics like "Gilda" and "Night and the City."
- 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_69ca83a38aa88190bf1bb80c4548b5e2 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc69fc0e4c819080b60456375f94cd |
completed | April 1, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdba4bfd481908a5f33d39b8e7dd5 |
completed | April 3, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:06 p.m.