Triple

T19974015
Position Surface form Disambiguated ID Type / Status
Subject Luc Hoffmann E493639 entity
Predicate hasChild P369 FINISHED
Object Vera Michalski-Hoffmann 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: Vera Michalski-Hoffmann | Statement: [Luc Hoffmann, hasChild, Vera Michalski-Hoffmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vera Michalski-Hoffmann
Context triple: [Luc Hoffmann, hasChild, Vera Michalski-Hoffmann]
  • A. Vera Michalski-Hoffmann chosen
    Vera Michalski-Hoffmann is a Swiss-based publisher and philanthropist known for leading the Libella publishing group and supporting literary and environmental causes.
  • B. Wanda Krahelska-Filipowicz
    Wanda Krahelska-Filipowicz was a Polish socialist activist and resistance figure best known for her role in organizing aid for Jews during World War II and her involvement in the Polish underground.
  • C. Sonja Baranilkowa
    Sonja Baranilkowa is a fictional character from the animated television series "Spies."
  • D. Maria Mochnacz
    Maria Mochnacz is a British photographer and music video director best known for her long-running visual collaborations with musician PJ Harvey.
  • E. Barbara Karinska
    Barbara Karinska was a renowned costume designer best known for her innovative and influential work for ballet companies such as the New York City Ballet.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65bcb72048190aedb4f085ace0493 completed April 20, 2026, 5 p.m.
Created at: April 11, 2026, 3:23 p.m.