Triple
T22655162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Mahabharata (1989 film) |
E559203
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Johan Leysen |
—
|
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: Johan Leysen | Statement: [The Mahabharata (1989 film), stars, Johan Leysen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Johan Leysen Context triple: [The Mahabharata (1989 film), stars, Johan Leysen]
-
A.
Johan Leysen
chosen
Johan Leysen was a Belgian actor known for his extensive work in European cinema and television, including roles in international thrillers and art-house films.
-
B.
Wouter Vandenhaute
Wouter Vandenhaute is a Belgian businessman and media entrepreneur best known for his leadership role at top football club R.S.C. Anderlecht.
-
C.
Jef Teugels
Jef Teugels is a Belgian mathematician known for his contributions to probability theory and actuarial science.
-
D.
Cédric Van Styvendael
Cédric Van Styvendael is a French politician who serves as the mayor of the city of Villeurbanne, near Lyon.
-
E.
Dirk Van Saene
Dirk Van Saene is a Belgian fashion designer and influential member of the avant-garde Antwerp Six collective known for reshaping contemporary fashion in the 1980s.
- 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_69e245489dd88190b1f674acf61c8769 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765a97ac819095f21ccbdada1d0a |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 3:06 p.m.