Triple
T22899608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catch a Fire |
E568272
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Scion 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: Scion Films | Statement: [Catch a Fire, productionCompany, Scion Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scion Films Context triple: [Catch a Fire, productionCompany, Scion Films]
-
A.
Scion Films
chosen
Scion Films is a British film production company known for backing acclaimed dramas such as "The Constant Gardener."
-
B.
Imagine Films
Imagine Films is a film production division associated with the American entertainment company Imagine Entertainment, known for developing and producing motion pictures.
-
C.
Axon Films
Axon Films is a film production company known for producing the movie "Milk."
-
D.
Valoria Films
Valoria Films is a film distribution company known for handling the release of various international and independent movies.
-
E.
Cinelou Films
Cinelou Films is an independent American film production company known for producing character-driven dramas such as the 2014 film "Cake."
- 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_69f180155b1c8190a83eb6ec45387a1a |
completed | April 29, 2026, 3:50 a.m. |
Created at: April 17, 2026, 3:41 p.m.