Triple

T21234357
Position Surface form Disambiguated ID Type / Status
Subject Anne-Sophie Nyssen E523303 entity
Predicate name P16 FINISHED
Object Anne-Sophie Nyssen 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: Anne-Sophie Nyssen | Statement: [Anne-Sophie Nyssen, name, Anne-Sophie Nyssen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anne-Sophie Nyssen
Context triple: [Anne-Sophie Nyssen, name, Anne-Sophie Nyssen]
  • A. Anne-Sophie Nyssen chosen
    Anne-Sophie Nyssen is a Belgian academic and university leader who serves as rector of the University of Liège.
  • B. Silvy De Bie
    Silvy De Bie is a Belgian singer best known as the lead vocalist of the Eurodance group Sylver.
  • C. Tia Hellebaut
    Tia Hellebaut is a Belgian high jumper best known for winning the gold medal at the 2008 Beijing Olympic Games.
  • D. Annelies Verlinden
    Annelies Verlinden is a Belgian politician who serves as the country’s Minister of the Interior, overseeing domestic security and internal affairs.
  • E. Sabine Theunissen
    Sabine Theunissen is a stage and set designer known for her work on major opera and theater productions, including co-designing the production of Shostakovich’s opera "The Nose."
  • 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_69e0b512ad94819087942b2ed925185f completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7351e4b908190bc02f063e3822123 completed April 21, 2026, 8:28 a.m.
Created at: April 16, 2026, 3:46 p.m.