Triple
T22899624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catch a Fire |
E568272
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object | Marius Weyers |
—
|
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: Marius Weyers | Statement: [Catch a Fire, starredActor, Marius Weyers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marius Weyers Context triple: [Catch a Fire, starredActor, Marius Weyers]
-
A.
Marius Weyers
chosen
Marius Weyers is a South African actor best known internationally for his role in the film "The Gods Must Be Crazy" and for his extensive work in South African cinema and television.
-
B.
Marius de Jonge
Marius de Jonge is a Dutch biblical scholar known for his influential work on New Testament studies and early Christianity.
-
C.
Marius de Vries
Marius de Vries is a British composer, producer, and arranger known for his innovative work on film soundtracks and collaborations with prominent pop and electronic artists.
-
D.
Marius Burger
Marius Burger is an individual notable enough to be recognized as a distinguished bearer of the surname Burger.
-
E.
Jules Van den Eeden
Jules Van den Eeden was a conductor known for leading the premiere performance of César Franck’s *Symphonic Variations*.
- 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180155b1c8190a83eb6ec45387a1a |
completed | April 29, 2026, 3:50 a.m. |
Created at: April 17, 2026, 3:41 p.m.