Triple
T23388950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trash Fire |
E593957
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Snowfort Pictures |
—
|
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: Snowfort Pictures | Statement: [Trash Fire, productionCompany, Snowfort Pictures]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snowfort Pictures Context triple: [Trash Fire, productionCompany, Snowfort Pictures]
-
A.
Snowfort Pictures
chosen
Snowfort Pictures is an independent film production company known for producing genre-driven and cult-favorite horror, thriller, and sci-fi movies.
-
B.
Lewis Pictures
Lewis Pictures is a South Korean film production company known for backing acclaimed works such as Bong Joon-ho’s fantasy drama "Okja."
-
C.
Nomadic Pictures
Nomadic Pictures is a Canadian film and television production company known for producing series such as Hell on Wheels and other genre and drama projects.
-
D.
Indelible Pictures
Indelible Pictures is a film production company known for producing the skateboarding drama "Lords of Dogtown."
-
E.
Lopert Pictures
Lopert Pictures was an American film distribution company known for releasing foreign and art-house films to U.S. audiences, often in collaboration with major studios.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a499bad88190afca1afb2e3fddb0 |
completed | April 29, 2026, 6:26 a.m. |
Created at: April 17, 2026, 5:35 p.m.