Triple
T20339432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Algiers (1938 film) |
E495699
|
entity |
| Predicate | leadCharacter |
P1668
|
FINISHED |
| Object | Pépé le Moko |
—
|
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: Pépé le Moko | Statement: [Algiers (1938 film), leadCharacter, Pépé le Moko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pépé le Moko Context triple: [Algiers (1938 film), leadCharacter, Pépé le Moko]
-
A.
Pépé le Moko
chosen
Pépé le Moko is a classic 1937 French crime drama film about a charismatic Parisian gangster hiding in the Casbah of Algiers, widely regarded as a landmark of poetic realism.
-
B.
Margès
Margès is a small commune in the Drôme department of southeastern France, situated within the administrative area of Romans-sur-Isère.
-
C.
Monsieur Klein
Monsieur Klein is a 1976 French drama film directed by Joseph Losey, starring Alain Delon as an art dealer in Nazi-occupied Paris who becomes entangled in a case of mistaken identity.
-
D.
Docteur Petiot
Docteur Petiot is a 1990 French crime drama film in which Michel Serrault portrays the infamous real-life serial killer Dr. Marcel Petiot.
-
E.
Léon
Léon is a French surname borne by various notable individuals across fields such as politics, arts, and academia.
- 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_69e0b4a1a09881908d97270d6971a25a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678342a0081908ede8006eb5506a3 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:23 a.m.