Triple

T22235277
Position Surface form Disambiguated ID Type / Status
Subject Police Rescue E549575 entity
Predicate starredActor P5563 FINISHED
Object Sonia Todd 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: Sonia Todd | Statement: [Police Rescue, starredActor, Sonia Todd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonia Todd
Context triple: [Police Rescue, starredActor, Sonia Todd]
  • A. Sonia Todd chosen
    Sonia Todd is an individual associated with the work "Shine," likely recognized for a notable role or contribution connected to that title.
  • B. Madeleine Eastoe
    Madeleine Eastoe is a celebrated Australian ballerina renowned for her long and distinguished career as a principal artist with The Australian Ballet.
  • C. Jacqueline Carlin
    Jacqueline Carlin is an American actress and former model best known for her film and television work in the 1970s and 1980s.
  • D. Susan Frowde
    Susan Frowde was the wife of British Royal Navy officer and celebrated Napoleonic Wars admiral Edward Pellew, 1st Viscount Exmouth.
  • E. Sara Maitland
    Sara Maitland is a British writer known for her feminist fiction, explorations of religion and spirituality, and later works on silence and solitary living.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf6d74c8190a1d8d8fc24a06bd1 completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:38 p.m.