Triple
T19095462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Royal Affair |
E467392
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Rasmus Heisterberg |
—
|
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: Rasmus Heisterberg | Statement: [A Royal Affair, screenwriter, Rasmus Heisterberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rasmus Heisterberg Context triple: [A Royal Affair, screenwriter, Rasmus Heisterberg]
-
A.
Rasmus Heisterberg
chosen
Rasmus Heisterberg is a Danish screenwriter and filmmaker known for his work on acclaimed Nordic crime thrillers and literary adaptations.
-
B.
Rasmus Jacobsen
Rasmus Jacobsen is a personal name shared by multiple individuals, typically of Danish or Scandinavian origin.
-
C.
Rasmus Hedegaard
Rasmus Hedegaard is a Danish DJ and music producer known for his electronic and pop-oriented remixes and collaborations.
-
D.
Jesper Rasmussen
Jesper Rasmussen is a Danish professional footballer known for playing as a forward in Denmark’s top leagues.
-
E.
Rasmus Christensen
Rasmus Christensen is a Danish professional footballer known for playing as a defender in European club competitions.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e368f20c8190bd84d2ba320991ac |
completed | April 20, 2026, 8:27 a.m. |
Created at: April 10, 2026, 12:04 p.m.