Triple

T22101720
Position Surface form Disambiguated ID Type / Status
Subject Frieda E546186 entity
Predicate starredActor P5563 FINISHED
Object Mai Zetterling 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: Mai Zetterling | Statement: [Frieda, starredActor, Mai Zetterling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mai Zetterling
Context triple: [Frieda, starredActor, Mai Zetterling]
  • A. Mai Zetterling chosen
    Mai Zetterling was a Swedish actress and director known for her intense screen presence in European cinema and her later work as a pioneering feminist filmmaker.
  • B. Ulla Nykvist
    Ulla Nykvist was the wife of renowned Swedish cinematographer Sven Nykvist.
  • C. Anna-Eva Bergman
    Anna-Eva Bergman was a Norwegian-born painter known for her abstract, minimalist works that often explored light, landscape, and texture through the use of metal leaf and muted color palettes.
  • D. Viveca Lindfors
    Viveca Lindfors was a Swedish-American actress known for her intense, versatile performances in European and Hollywood films and on stage from the 1940s through the late 20th century.
  • E. Eva Andersson
    Eva Andersson is a Swedish former model and physician best known for her work with Sports Illustrated and her marriage to hedge fund manager Glenn Dubin.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129163b908190b63ace06016f4db8 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.