Triple
T20784754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Singing Nun |
E511598
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Henry Koster |
—
|
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: Henry Koster | Statement: [The Singing Nun, director, Henry Koster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Koster Context triple: [The Singing Nun, director, Henry Koster]
-
A.
Henry Koster
chosen
Henry Koster was a German-born American film director best known for his work in Hollywood during the 1930s–1950s, including popular comedies, dramas, and family films.
-
B.
Bert Shefter
Bert Shefter was a film composer best known for his collaborations on mid-20th-century science fiction and horror movie scores.
-
C.
Raymond Kravis
Raymond Kravis was an American oil and gas investor and philanthropist, best known as the father of financier Henry Kravis and namesake of several major cultural and educational institutions.
-
D.
Herman Varnick
Herman Varnick is the villainous veterinarian and primary antagonist in the family comedy film "Beethoven."
-
E.
Gene Rosow
Gene Rosow is a film and television producer best known for his work on family-oriented and nature-themed projects such as the movie "Zeus and Roxanne."
- 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_69e0b4cac7a48190a715cb3d545df2b4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c28b4ce88190a45f1c99b58d18eb |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:38 p.m.