Triple
T21965913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean-Paul Rappeneau |
E542455
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Bon voyage |
—
|
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: Bon voyage | Statement: [Jean-Paul Rappeneau, directed, Bon voyage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bon voyage Context triple: [Jean-Paul Rappeneau, directed, Bon voyage]
-
A.
Bon Voyage
Bon Voyage is a retail store, likely themed around travel, that offers related goods and accessories to customers.
-
B.
Bon Voyage
chosen
Bon Voyage is a 2003 French romantic thriller film, directed by Jean-Paul Rappeneau, that intertwines political intrigue and personal drama on the eve of World War II.
-
C.
Bon Voyage
"Bon Voyage" is a song by the New Zealand rock band Oceanic.
-
D.
Viagem
"Viagem" is a celebrated poetry collection by Brazilian writer Cecília Meireles, known for its lyrical introspection and central role in Brazilian modernist literature.
-
E.
Around the Horn
Around the Horn is a long-running ESPN sports debate show where a host scores and moderates fast-paced discussions among a rotating panel of sports journalists.
- 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_69e0c47fab1081908dc74a6545dbb051 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1245aabf88190a44564e6eaaa94ce |
completed | April 28, 2026, 9:19 p.m. |
Created at: April 16, 2026, 8:01 p.m.