Triple
T23029922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colosseum kino |
E573428
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | Nordisk Film Kino |
—
|
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: Nordisk Film Kino | Statement: [Colosseum kino, operator, Nordisk Film Kino]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nordisk Film Kino Context triple: [Colosseum kino, operator, Nordisk Film Kino]
-
A.
Nordisk Film Cinemas
chosen
Nordisk Film Cinemas is a major Scandinavian cinema chain operating movie theaters primarily in Denmark and Norway under the ownership of Nordisk Film.
-
B.
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.
-
C.
Multikino
Multikino is a major Polish multiplex cinema chain operating modern movie theaters across numerous cities in Poland and parts of Europe.
-
D.
Filmstaden AB
Filmstaden AB is Sweden’s largest cinema chain, operating multiplex movie theaters across the country.
-
E.
Filmhuset
Filmhuset is a prominent Swedish film center and office complex in Stockholm that houses the Swedish Film Institute and serves as a hub for the country’s film industry and culture.
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f184803e908190b1e58545b9c3d587 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.