Triple
T20741282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Armored |
E510446
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jean Reno |
—
|
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: Jean Reno | Statement: [Armored, starring, Jean Reno]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean Reno Context triple: [Armored, starring, Jean Reno]
-
A.
Jean Reno
chosen
Jean Reno is a French actor known for his roles in films such as Léon: The Professional, The Big Blue, and Mission: Impossible.
-
B.
Jean-Marc Barr
Jean-Marc Barr is a French-American actor and director best known for his leading role in "The Big Blue" and frequent collaborations with filmmaker Lars von Trier.
-
C.
Paul Cluzet
Paul Cluzet is the son of acclaimed French actor François Cluzet.
-
D.
James Thierrée
James Thierrée is a Swiss-born actor, director, and contemporary circus performer known for his inventive, physical, and often surreal stage productions that blend mime, dance, and acrobatics.
-
E.
Raymond Huppert
Raymond Huppert was the father of acclaimed French actress Isabelle Huppert.
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c20e76ac8190985203b2c17aca14 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:32 p.m.