Triple

T10457449
Position Surface form Disambiguated ID Type / Status
Subject Owning Mahowny E246582 entity
Predicate stars P1956 FINISHED
Object Sonja Smits E824113 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: Sonja Smits | Statement: [Owning Mahowny, stars, Sonja Smits]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonja Smits
Context triple: [Owning Mahowny, stars, Sonja Smits]
  • A. Sonja Smits chosen
    Sonja Smits is a Canadian actress known for her work in film and television, particularly in genre and dramatic roles.
  • B. Kate Nauta
    Kate Nauta is an American fashion model, actress, and singer best known for her role as the villainous Lola in the action film "Transporter 2."
  • C. Barbara Smits
    Barbara Smits was the former wife of Emmy-winning American actor Jimmy Smits and the mother of his two children.
  • D. Francine Houben
    Francine Houben is a renowned Dutch architect and creative director of the architecture firm Mecanoo, known for her human-centered, context-sensitive designs such as the Library of Birmingham and Delft University of Technology Library.
  • E. Wivina Demeester
    Wivina Demeester is a Belgian politician known for her long-standing role in Flemish and national politics, particularly in public finance and infrastructure.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fe4a56e08190ab56d762d6a91b01 completed April 7, 2026, 12:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69d87f182cb481909f838d6d1dfa7e79 completed April 10, 2026, 4:39 a.m.
Created at: April 6, 2026, 12:18 p.m.