Triple

T14874186
Position Surface form Disambiguated ID Type / Status
Subject Otherhood E349823 entity
Predicate starring P1507 FINISHED
Object Becki Newton E1006457 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: Becki Newton | Statement: [Otherhood, starring, Becki Newton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Becki Newton
Context triple: [Otherhood, starring, Becki Newton]
  • A. Becki Newton chosen
    Becki Newton is an American actress best known for her comedic television roles, particularly in popular network sitcoms and dramedies.
  • B. Becky Clements
    Becky Clements is a television producer known for her executive production work on series such as "Good Behavior."
  • C. Becky McIntyre
    Becky McIntyre is a fictional character known as the daughter of Trapper John McIntyre from the M*A*S*H television franchise.
  • D. Becky Leeman
    Becky Leeman is the ambitious, manipulative beauty pageant contestant and primary antagonist in the dark comedy film "Drop Dead Gorgeous."
  • E. Becky Spratford
    Becky Spratford is a readers’ advisory librarian, consultant, and author known for her expertise in serving leisure readers, particularly in the horror genre.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5e3e5d48190a132f2cf012b01e2 completed April 15, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69feae005644819098937cedb53202c5 completed May 9, 2026, 3:46 a.m.
Created at: April 10, 2026, 1:55 a.m.