Triple
T22210553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Van Helsing |
E548932
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Stillking 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: Stillking Films | Statement: [Van Helsing, productionCompany, Stillking Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stillking Films Context triple: [Van Helsing, productionCompany, Stillking Films]
-
A.
Stillking Films
chosen
Stillking Films is an international film and television production company known for servicing and co-producing major Hollywood and European projects.
-
B.
Kingsgate Films
Kingsgate Films is a film production company best known for producing the stoner comedy "Harold & Kumar Go to White Castle."
-
C.
Dimension Films
Dimension Films is an American film production and distribution company best known for releasing popular horror and genre franchises such as Scream and Scary Movie.
-
D.
Alive Films
Alive Films was an independent American film production company known for backing distinctive genre and auteur-driven movies in the 1980s and early 1990s.
-
E.
See-Saw Films
See-Saw Films is a British-Australian film and television production company known for acclaimed works such as the Academy Award–winning drama "The King’s Speech."
- 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b2bcf748190a9721f0c9ae17e70 |
completed | April 28, 2026, 9:48 p.m. |
Created at: April 16, 2026, 8:36 p.m.