Triple

T17984839
Position Surface form Disambiguated ID Type / Status
Subject Stacy Barrett E430202 entity
Predicate portrayedBy P1507 FINISHED
Object April Bowlby 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: April Bowlby | Statement: [Stacy Barrett, portrayedBy, April Bowlby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: April Bowlby
Context triple: [Stacy Barrett, portrayedBy, April Bowlby]
  • A. April Bowlby chosen
    April Bowlby is an American actress best known for her television roles in series such as Drop Dead Diva, Two and a Half Men, and Doom Patrol.
  • B. Dorothy Bishop
    Dorothy Bishop is a British neuropsychologist and professor renowned for her research on developmental language disorders and advocacy for open science and research integrity.
  • C. Ann Belsky
    Ann Belsky was a costume designer and the late wife of Canadian actor Rick Moranis.
  • D. John Bowlby
    John Bowlby was a British psychiatrist and psychoanalyst best known for developing attachment theory, which transformed understanding of child development and the impact of early relationships on later mental health.
  • E. Michael Tronick
    Michael Tronick is an American film editor known for his work on numerous major Hollywood productions across several decades.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29a27b081909a128a6b978eabf8 completed April 19, 2026, 10:46 a.m.
Created at: April 10, 2026, 10:23 a.m.