Triple
T18601020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Down from the Mountain |
E454618
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Nick Doob |
—
|
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: Nick Doob | Statement: [Down from the Mountain, director, Nick Doob]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nick Doob Context triple: [Down from the Mountain, director, Nick Doob]
-
A.
Nick Doob
chosen
Nick Doob is an American cinematographer and documentary filmmaker known for his work on influential political and social-issue films.
-
B.
Danny Jacobson
Danny Jacobson is an American television writer and producer best known for co-creating the hit sitcom "Mad About You."
-
C.
Damon Gough
Damon Gough is an English singer-songwriter and multi-instrumentalist best known for recording under the stage name Badly Drawn Boy.
-
D.
Jason Ratcliff
Jason Ratcliff is an American NASCAR crew chief best known for leading competitive Cup and Xfinity Series teams, particularly with Joe Gibbs Racing.
-
E.
Mark Dooley
Mark Dooley is a film producer best known for his work on the 2013 biographical drama "Jobs," which chronicles the life of Apple co-founder Steve Jobs.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5475112608190acacc5ac7a08c4a0 |
completed | April 19, 2026, 9:21 p.m. |
Created at: April 10, 2026, 11:45 a.m.