Triple

T5303467
Position Surface form Disambiguated ID Type / Status
Subject Always E120038 entity
Predicate cinematographer P1953 FINISHED
Object Mikael Salomon E80140 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: Mikael Salomon | Statement: [Always, cinematographer, Mikael Salomon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mikael Salomon
Context triple: [Always, cinematographer, Mikael Salomon]
  • A. Mikael Salomon chosen
    Mikael Salomon is a Danish cinematographer and film director known for his visually striking work on major Hollywood films and television series.
  • B. Mikael Boghosian
    Mikael Boghosian is the Armenian medical student protagonist of the 2016 historical drama film "The Promise," whose experiences depict the human impact of the Armenian Genocide.
  • C. Mikael Odenberg
    Mikael Odenberg is a Swedish politician who served as Sweden’s Minister for Defence and has been a prominent member of the Moderate Party.
  • D. Mikael Andersson
    Mikael Andersson is a Swedish ice hockey player best known for his significant contributions to the Malmö Redhawks organization.
  • E. Michael Elias
    Michael Elias is an American screenwriter, actor, and director best known for co-writing the hit comedy film "The Jerk" starring Steve Martin.
  • 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_69bd44704be88190acdb2ac481b0ff55 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd851b685c8190b7ed8c762a807395 completed March 20, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf10f3b9ac81909cd2ca2278b11d3e completed March 21, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:53 p.m.