Triple

T14694642
Position Surface form Disambiguated ID Type / Status
Subject Lili Elbe E345121 entity
Predicate spouse P13 FINISHED
Object Gerda Wegener E345124 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: Gerda Wegener | Statement: [Lili Elbe, spouse, Gerda Wegener]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gerda Wegener
Context triple: [Lili Elbe, spouse, Gerda Wegener]
  • A. Gerda Wegener chosen
    Gerda Wegener was a Danish illustrator and painter known for her Art Deco style and for her depictions of her spouse Lili Elbe, one of the first recipients of gender confirmation surgery.
  • B. Natalie Bauer-Lechner
    Natalie Bauer-Lechner was an Austrian violist and close confidante of Gustav Mahler, known for her detailed recollections of the composer and his work.
  • C. Albertina Rasch
    Albertina Rasch was an influential early 20th-century choreographer and dance director known for her work on Broadway and in Hollywood films.
  • D. Gerda Holmberg
    Gerda Holmberg was the wife of Swedish poet and Nobel laureate Erik Axel Karlfeldt.
  • E. Ursula Maria Martius
    Ursula Maria Martius, better known as Ursula Franklin, was a German-Canadian physicist, metallurgist, and pacifist renowned for her work in materials science and her influential writings on technology and society.
  • 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_69d822e34b348190ada4d1cdb6c7c226 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb586e7108190be644db9cf9a4d99 completed April 14, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde18e279c8190814f90e947734541 completed May 8, 2026, 1:13 p.m.
Created at: April 10, 2026, 1:28 a.m.