Triple

T10226603
Position Surface form Disambiguated ID Type / Status
Subject Ian Holm E243220 entity
Predicate spouse P13 FINISHED
Object Sophie de Stempel E243220 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: Sophie de Stempel | Statement: [Ian Holm, spouse, Sophie de Stempel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sophie de Stempel
Context triple: [Ian Holm, spouse, Sophie de Stempel]
  • A. Sophie de Stempel chosen
    Sophie de Stempel is a British artist best known as the widow of acclaimed actor Sir Ian Holm.
  • B. Catherine De Bolle
    Catherine De Bolle is a Belgian police official and former Commissioner General of the Belgian Federal Police who serves as the Executive Director of Europol.
  • C. Sonia Bompastor
    Sonia Bompastor is a former French international footballer and current manager, best known as a standout left-sided player for club and country and later as head coach of Olympique Lyonnais Féminin.
  • D. Stéphanie Von Euw
    Stéphanie Von Euw is a French politician who serves as the mayor of the city of Pontoise in the Île-de-France region.
  • E. Christine Leunens
    Christine Leunens is a New Zealand–based Belgian-American novelist best known for her book "Caging Skies," which was adapted into the Oscar-winning film "Jojo Rabbit."
  • 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d1fa98a48190a5caf6b6003bc14c completed April 7, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f71fb4048190a36f1fe499729332 completed April 9, 2026, 12:47 a.m.
Created at: April 6, 2026, 11:17 a.m.