Triple

T20897874
Position Surface form Disambiguated ID Type / Status
Subject Naomi Watts E514587 entity
Predicate hasChild P369 FINISHED
Object Sasha Schreiber 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: Sasha Schreiber | Statement: [Naomi Watts, hasChild, Sasha Schreiber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sasha Schreiber
Context triple: [Naomi Watts, hasChild, Sasha Schreiber]
  • A. Sasha Schreiber chosen
    Sasha Schreiber is the son of actors Naomi Watts and Liev Schreiber.
  • B. Bianca Andreescu
    Bianca Andreescu is a Canadian professional tennis player best known for winning the 2019 US Open and becoming the first Canadian to claim a Grand Slam singles title.
  • C. Tessa Shapovalova
    Tessa Shapovalova is a former professional tennis player and coach best known as the mother and early coach of Canadian tennis star Denis Shapovalov.
  • D. Serhiy Ostapenko
    Serhiy Ostapenko was a Ukrainian politician who briefly served as head of government of the Ukrainian People's Republic during its struggle for independence after World War I.
  • E. Iga Świątek
    Iga Świątek is a Polish professional tennis player and multiple Grand Slam champion known for her dominant baseline game and time spent as world No. 1 in women’s singles.
  • 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8f826788190b11008cc94b2a4e4 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.