Triple
T17544095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeanette MacDonald |
E427278
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | One Hour with You |
—
|
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: One Hour with You | Statement: [Jeanette MacDonald, notableWork, One Hour with You]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: One Hour with You Context triple: [Jeanette MacDonald, notableWork, One Hour with You]
-
A.
One Hour with You
chosen
One Hour with You is a 1932 pre-Code musical romantic comedy film directed by Ernst Lubitsch and George Cukor, starring Maurice Chevalier and Jeanette MacDonald.
-
B.
Alright for an Hour
"Alright for an Hour" is a song featured on the 2014 album *Atlantic Crossing* by Scottish indie rock band Franz Ferdinand.
-
C.
This One's for You
"This One's for You" is a 1976 pop album by Barry Manilow that includes the hit single "Looks Like We Made It" and helped solidify his popularity in the late 1970s.
-
D.
With You
"With You" is a song featured on the album "Unpredictable" by American R&B singer Jamie Foxx.
-
E.
With You
"With You" is a track by American rapper Lil Wayne from his album "I Am Not a Human Being."
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4545fe29c8190a586c75419fa14ea |
completed | April 19, 2026, 4:04 a.m. |
Created at: April 10, 2026, 5:49 a.m.