Triple
T18826460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Monsieur Verdoux |
E460399
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Arthur Hohl |
—
|
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: Arthur Hohl | Statement: [Monsieur Verdoux, castMember, Arthur Hohl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arthur Hohl Context triple: [Monsieur Verdoux, castMember, Arthur Hohl]
-
A.
Arthur Hohl
chosen
Arthur Hohl was an American character actor known for his supporting roles in numerous Hollywood films during the 1930s and 1940s.
-
B.
George Boemler
George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
-
C.
Charles Bohl
Charles Bohl is a screenwriter best known for his work on the 2002 psychological thriller film "Swimfan."
-
D.
Charles Rumback
Charles Rumback is an American jazz drummer and composer known for his work in Chicago’s experimental and improvisational music scene.
-
E.
Charles Leickert
Charles Leickert was a 19th-century Dutch painter renowned for his atmospheric winter landscapes and cityscapes of the Netherlands.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a6bec7b08190b040ec8b3693f037 |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 10, 2026, 11:56 a.m.