Triple

T14694757
Position Surface form Disambiguated ID Type / Status
Subject Gerda Wegener E345124 entity
Predicate spouse P13 FINISHED
Object Lili Elbe E345121 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: Lili Elbe | Statement: [Gerda Wegener, spouse, Lili Elbe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lili Elbe
Context triple: [Gerda Wegener, spouse, Lili Elbe]
  • A. Lili Elbe chosen
    Lili Elbe was a Danish transgender woman and pioneering recipient of early gender confirmation surgeries, whose life and transition inspired the novel and film "The Danish Girl."
  • B. Regina Jonas
    Regina Jonas was the first woman to be ordained as a rabbi, a pioneering figure in 20th-century German Reform Judaism and a symbol of both religious innovation and Holocaust-era persecution.
  • C. Lydia Mertz
    Lydia Mertz is a supporting character in the darkly comedic crime film "To Die For," which satirizes media obsession and ambition.
  • D. Hanna Hilsdorf
    Hanna Hilsdorf is a German actress known for her role in the crime drama film "In the Fade" and for her work in contemporary German cinema and television.
  • E. Anneliese Michel
    Anneliese Michel was a German woman whose controversial 1970s exorcism and death from malnutrition inspired debates over religious practice, mental illness, and criminal negligence.
  • 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.