Triple
T22891028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knight and Day |
E568039
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Tree Line Films |
—
|
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: Tree Line Films | Statement: [Knight and Day, productionCompany, Tree Line Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tree Line Films Context triple: [Knight and Day, productionCompany, Tree Line Films]
-
A.
Tree Line Films
chosen
Tree Line Films is a film production company known for working on major feature films, including the 2007 Western thriller "3:10 to Yuma."
-
B.
BorderLine Films
BorderLine Films is an independent film production company known for producing dark, character-driven dramas and psychological thrillers.
-
C.
Wildflower Films
Wildflower Films is a film production company known for producing the Australian drama feature "The Daughter."
-
D.
MadRiver Pictures
MadRiver Pictures is a film production company known for financing and producing high-profile, director-driven feature films.
-
E.
Firefly Films
Firefly Films is a film production company known for producing the darkly comedic thriller "Come to Daddy."
- 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f17fc59e108190a22f90c2439830fb |
completed | April 29, 2026, 3:49 a.m. |
Created at: April 17, 2026, 3:40 p.m.