Triple

T13518317
Position Surface form Disambiguated ID Type / Status
Subject Bille August E322824 entity
Predicate spouse P13 FINISHED
Object Pernilla August E209458 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: Pernilla August | Statement: [Bille August, spouse, Pernilla August]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pernilla August
Context triple: [Bille August, spouse, Pernilla August]
  • A. Pernilla August chosen
    Pernilla August is a Swedish actress and director best known internationally for playing Shmi Skywalker, Anakin Skywalker’s mother, in the Star Wars prequel films.
  • B. Ewa Westling
    Ewa Westling is a Swedish woman best known as the mother of Prince Daniel, Duke of Västergötland, who is married to Crown Princess Victoria of Sweden.
  • C. Harriet Andersson
    Harriet Andersson is a Swedish actress renowned for her collaborations with director Ingmar Bergman and her influential performances in mid-20th-century European cinema.
  • D. Lena Andersson
    Lena Andersson is a Swedish author and columnist known for her psychologically incisive novels and essays on politics, society, and human relationships.
  • E. Thilde Benz
    Thilde Benz was one of the children of German engineer and automobile pioneer Karl Benz.
  • 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_69d80766a21881909f21a1b7421d3b8a completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafa27f048190bed33a98e28c8d09 completed April 12, 2026, 2:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75d93a2608190a3a693bf4086a010 completed May 3, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:44 p.m.