Triple
T22103878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Education (2019 film) |
E546236
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Cory Finley |
—
|
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: Cory Finley | Statement: [Bad Education (2019 film), director, Cory Finley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cory Finley Context triple: [Bad Education (2019 film), director, Cory Finley]
-
A.
Cory Finley
chosen
Cory Finley is an American filmmaker and playwright best known for his darkly comedic and psychologically driven films such as "Thoroughbreds" and "Bad Education."
-
B.
Corey McCormick
Corey McCormick is an American bassist best known for his work with Neil Young and the rock band Lukas Nelson & Promise of the Real.
-
C.
Michael Farris
Michael Farris is an American lawyer and conservative activist best known for his leadership in the Christian homeschooling movement and his role in founding and guiding Patrick Henry College.
-
D.
Michael Dulaney
Michael Dulaney is an American country music songwriter known for penning hits for prominent Nashville artists.
-
E.
Ron Feemster
Ron Feemster is a music producer known for his work on the album "Afrodisiac."
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1291815f88190a6eaf73e444dc1c2 |
completed | April 28, 2026, 9:39 p.m. |
Created at: April 16, 2026, 8:30 p.m.