Triple

T22768237
Position Surface form Disambiguated ID Type / Status
Subject Robert Bresson E563183 entity
Predicate notableWork P4 FINISHED
Object Pickpocket 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: Pickpocket | Statement: [Robert Bresson, notableWork, Pickpocket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pickpocket
Context triple: [Robert Bresson, notableWork, Pickpocket]
  • A. Pickpocket chosen
    Pickpocket is a 1959 French drama film by Robert Bresson, renowned for its minimalist style and existential exploration of crime, guilt, and redemption.
  • B. Burglar
    "Burglar" is a 1974 blues album by influential American guitarist and singer Freddie King, showcasing his powerful playing and soulful vocals.
  • C. Ladros
    Ladros is a highland region in J.R.R. Tolkien’s Beleriand, known as the northern part of Dorthonion and the fief granted to the House of Bëor.
  • D. Dieblich
    Dieblich is a small municipality in western Germany’s Rhineland-Palatinate region, situated along the Moselle River and known for its winegrowing and scenic surroundings.
  • E. Hoodlum
    Hoodlum is a 1997 American crime drama film about the Harlem underworld during the 1930s, focusing on the conflict between Black gangsters and the Italian mob.
  • 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a81d3348190b005a43a5e03d406 completed April 29, 2026, 3:26 a.m.
Created at: April 17, 2026, 3:27 p.m.