Triple

T9394771
Position Surface form Disambiguated ID Type / Status
Subject Silkwood E226115 entity
Predicate cinematographyBy P1953 FINISHED
Object Miroljub Dikosavljevic E226115 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: Miroljub Dikosavljevic | Statement: [Silkwood, cinematographyBy, Miroljub Dikosavljevic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miroljub Dikosavljevic
Context triple: [Silkwood, cinematographyBy, Miroljub Dikosavljevic]
  • A. Miroljub Dikosavljevic chosen
    Miroljub Dikosavljevic is a cinematographer known for his work on the film "Silkwood."
  • B. Mirko Cvetković
    Mirko Cvetković is a Serbian economist and politician who served as the country's prime minister in the late 2000s and early 2010s.
  • C. Ljubomir Ilić
    Ljubomir Ilić was a Yugoslav aircraft designer best known for co-designing the Ikarus IK-2 fighter aircraft.
  • D. Đuro Đaković
    Đuro Đaković was a prominent Yugoslav communist leader and revolutionary figure active in the early 20th century labor and workers’ movement.
  • E. Dragan Džajić
    Dragan Džajić is a legendary Serbian (Yugoslav) footballer widely regarded as one of the greatest left wingers in European football history.
  • 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_69ca842f7e3481908bf5bcf52e032dbd completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd511150008190be04142e477e8bf1 completed April 1, 2026, 5:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1010ffcd4819088edafbdb43c2c00 completed April 4, 2026, 12:16 p.m.
Created at: March 30, 2026, 7:45 p.m.