Triple

T40964
Position Surface form Disambiguated ID Type / Status
Subject Greta Thunberg E807 entity
Predicate coAuthorWith P398 FINISHED
Object Malena Ernman E5325 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: Malena Ernman | Statement: [Greta Thunberg, coAuthorWith, Malena Ernman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malena Ernman
Context triple: [Greta Thunberg, coAuthorWith, Malena Ernman]
  • A. Malena Ernman chosen
    Malena Ernman is a Swedish opera singer and environmental activist known both for her acclaimed mezzo-soprano career and as the mother of climate activist Greta Thunberg.
  • B. Celeste Holm
    Celeste Holm was an American actress best known for her Academy Award–winning performance in "Gentleman's Agreement" and her work on stage and screen during Hollywood's Golden Age.
  • C. Fay Wray
    Fay Wray was a Canadian-American actress best known for her iconic role as the damsel Ann Darrow in the classic 1933 film "King Kong."
  • D. Lucille Sheardown
    Lucille Sheardown was one of the later wives of American inventor Lee de Forest, associated with his personal life rather than his pioneering work in radio and electronics.
  • E. Maxine Singer
    Maxine Singer is an American molecular biologist renowned for her pioneering work in genetics and for her leadership in shaping ethical guidelines for recombinant DNA research.
  • 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_69a247a8f6c08190bac804906d62ed5a completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a24ae0b7c4819092220568e8e52ad5 completed Feb. 28, 2026, 1:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69a25ab3438c81908ff16eb23a09fea7 completed Feb. 28, 2026, 3:02 a.m.
Created at: Feb. 28, 2026, 1:46 a.m.