Triple

T15311629
Position Surface form Disambiguated ID Type / Status
Subject I Feel Pretty E366051 entity
Predicate director P255 FINISHED
Object Abby Kohn E512522 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: Abby Kohn | Statement: [I Feel Pretty, director, Abby Kohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abby Kohn
Context triple: [I Feel Pretty, director, Abby Kohn]
  • A. Abby Kohn chosen
    Abby Kohn is an American screenwriter and director best known for co-writing popular romantic comedies such as "He's Just Not That Into You" and "Never Been Kissed."
  • B. Abby Buchman
    Abby Buchman is a central character in the drama film "Rachel Getting Married," around whom much of the story’s emotional tension and family dynamics revolve.
  • C. Abigail Johnson
    Abigail Johnson is an American billionaire businesswoman who serves as the CEO of Fidelity Investments, one of the largest asset management firms in the world.
  • D. Abby McGrew
    Abby McGrew is an American philanthropist best known as the wife of former NFL quarterback Eli Manning.
  • E. Abby Clark
    Abby Clark is a 911 emergency call center operator and main character from the television series "9-1-1," portrayed by Connie Britton.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03cd2d5a88190aead748920f93d47 completed April 16, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8a20c1881909b387aed6f532c3d completed May 9, 2026, 9:04 a.m.
Created at: April 10, 2026, 3:16 a.m.