Triple
T10367858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heartbreaker |
E244300
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Jacques Frantz |
E1025805
|
NE FINISHED |
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: Jacques Frantz | Statement: [Heartbreaker, castMember, Jacques Frantz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jacques Frantz Context triple: [Heartbreaker, castMember, Jacques Frantz]
-
A.
Jacques Frantz
chosen
Jacques Frantz was a French actor and renowned voice dubber, best known for his work in film, theater, and as the French voice of major international stars.
-
B.
Jacques Defforey
Jacques Defforey was a French businessman best known as one of the founders of the multinational retail corporation Carrefour.
-
C.
Jean-Marie Dreujou
Jean-Marie Dreujou is a French cinematographer known for his visually rich work on films such as "Two Brothers" and other major European productions.
-
D.
Pierre Lafue
Pierre Lafue was a French writer and intellectual whose legacy is honored by a literary foundation prize bearing his name.
-
E.
Louis Jean Heydt
Louis Jean Heydt was an American character actor known for his numerous supporting roles in Hollywood films from the 1930s through the 1950s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e97106448190a075948e63184f47 |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a0e90e48190af6b802697d3256f |
completed | May 3, 2026, 8:40 a.m. |
Created at: April 6, 2026, noon