Triple
T23140203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brooklyn's Finest |
E577439
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | John Langley |
—
|
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: John Langley | Statement: [Brooklyn's Finest, producer, John Langley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Langley Context triple: [Brooklyn's Finest, producer, John Langley]
-
A.
John Langley
chosen
John Langley was an American television producer best known for pioneering the reality TV genre with the long-running law-enforcement series "Cops."
-
B.
John Langley Howard
John Langley Howard was an American painter and muralist associated with the Social Realist movement, known for his New Deal–era public artworks in San Francisco.
-
C.
Neal Langford
Neal Langford is a musician best known as an early bassist for the indie rock band The Shins.
-
D.
Bill Langworthy
Bill Langworthy is a television producer best known for his work on reality and docu-series, including serving as executive producer of "Candidly Nicole."
-
E.
Andrew Lanham
Andrew Lanham is an American screenwriter known for his collaborations with director Destin Daniel Cretton on acclaimed films such as "Just Mercy."
- 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_69e245f8e6248190ba3d58e068b4dccb |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ec922b481908084eee6a95aef83 |
completed | April 29, 2026, 4:53 a.m. |
Created at: April 17, 2026, 4 p.m.