Triple

T18576916
Position Surface form Disambiguated ID Type / Status
Subject Sven Lindqvist E454009 entity
Predicate spouse P13 FINISHED
Object Agnes Heller 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: Agnes Heller | Statement: [Sven Lindqvist, spouse, Agnes Heller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agnes Heller
Context triple: [Sven Lindqvist, spouse, Agnes Heller]
  • A. Ágnes Heller chosen
    Ágnes Heller was a prominent Hungarian philosopher and member of the Budapest School, known for her work in ethics, political philosophy, and critiques of totalitarianism.
  • B. Agnes Soral
    Agnes Soral is a French actress known for her work in film, television, and theater since the late 1970s.
  • C. Gerda Hedwig Lerner
    Gerda Hedwig Lerner was an Austrian-born American historian and pioneering feminist scholar who helped establish women’s history as a recognized academic field.
  • D. Paula Kast
    Paula Kast is a member of the Kast family, known primarily as a close relative of Chilean politician Michael Kast.
  • E. Sissela Bok
    Sissela Bok is a Swedish-born American philosopher and ethicist known for her influential work on lying, moral choice, and bioethics.
  • 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e543cc94f081909b76c3d488ed5637 completed April 19, 2026, 9:06 p.m.
Created at: April 10, 2026, 11:43 a.m.