Triple
T23231114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunger (1966 film) |
E581155
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Norsk Film |
—
|
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: Norsk Film | Statement: [Hunger (1966 film), productionCompany, Norsk Film]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norsk Film Context triple: [Hunger (1966 film), productionCompany, Norsk Film]
-
A.
Norsk Film
chosen
Norsk Film was a major Norwegian film production company that played a central role in the country’s cinema industry throughout much of the 20th century.
-
B.
Norwegian Film Institute
The Norwegian Film Institute is Norway’s national agency responsible for supporting, promoting, and preserving Norwegian cinema and film culture.
-
C.
Nordisk Film
Nordisk Film is a major Danish entertainment company and one of the world’s oldest film studios, known for producing and distributing films across the Nordic region.
-
D.
Norwegian cinema network
The Norwegian cinema network is a nationwide chain of movie theaters in Norway that operates and coordinates cinemas such as Colosseum kino.
-
E.
Svensk Filmindustri
Svensk Filmindustri is a major Swedish film production and distribution company, historically one of the country’s most influential 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f19231ef908190a791b4967916a66f |
completed | April 29, 2026, 5:08 a.m. |
Created at: April 17, 2026, 4:09 p.m.