Triple

T7843370
Position Surface form Disambiguated ID Type / Status
Subject Irma Frost E181857 entity
Predicate sibling P363 FINISHED
Object Lesley Frost E117149 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: Lesley Frost | Statement: [Irma Frost, sibling, Lesley Frost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lesley Frost
Context triple: [Irma Frost, sibling, Lesley Frost]
  • A. Lesley Frost chosen
    Lesley Frost was an American writer, educator, and lecturer, best known as the daughter of poet Robert Frost and for her work promoting literature and her father's legacy.
  • B. Jane Fulks
    Jane Fulks is the birth name of Jane Wyman, the Academy Award–winning American actress and first wife of Ronald Reagan.
  • C. Lizz Winstead
    Lizz Winstead is an American comedian, writer, and political satirist best known as a co-creator and former head writer of the television news parody program The Daily Show.
  • D. Nicole Barber
    Nicole Barber is a central character in the film "Marriage Story," portrayed as an actress navigating a painful divorce and personal rediscovery.
  • E. Betsy McCaughey
    Betsy McCaughey is an American politician, writer, and former Lieutenant Governor of New York known for her conservative commentary and opposition to certain health care reforms.
  • 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_69ca8285d6488190a95d4c02d7354b53 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb163b32688190b463a9cd8fa3c690 completed March 31, 2026, 12:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5aded4048190b18604963784352c completed March 31, 2026, 5:25 a.m.
Created at: March 30, 2026, 4:48 p.m.