Triple
T18239848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shine a Light |
E436779
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Michael Cohl |
—
|
NE NERFINISHED |
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: Michael Cohl | Statement: [Shine a Light, producer, Michael Cohl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Cohl Context triple: [Shine a Light, producer, Michael Cohl]
-
A.
Michael Cohl
chosen
Michael Cohl is a renowned Canadian concert promoter and producer best known for organizing large-scale international tours for major rock acts like The Rolling Stones.
-
B.
Mitch Rouse
Mitch Rouse is an American actor, comedian, and writer known for his work in film and television, including co-creating the series "Strangers with Candy" and appearing in numerous comedic roles.
-
C.
Eric McLeod
Eric McLeod is a film producer known for his work on major Hollywood action and genre movies, including the monster crossover blockbuster "Godzilla vs. Kong."
-
D.
Jason Crouse
Jason Crouse is a fictional defense investigator and love interest of Alicia Florrick on the legal drama television series "The Good Wife."
-
E.
Eric Danchick
Eric Danchick is a film producer known for his work on the movie "Bound 2."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f7e19d9881908d6a227528241e4a |
completed | April 19, 2026, 3:42 p.m. |
Created at: April 10, 2026, 10:33 a.m.