Triple

T23306338
Position Surface form Disambiguated ID Type / Status
Subject Karen Arnold E590445 entity
Predicate hasMother P1909 FINISHED
Object Norma Arnold 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: Norma Arnold | Statement: [Karen Arnold, hasMother, Norma Arnold]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norma Arnold
Context triple: [Karen Arnold, hasMother, Norma Arnold]
  • A. Norma Arnold chosen
    Norma Arnold is the caring and resilient mother of Kevin Arnold in the coming-of-age television series "The Wonder Years."
  • B. Norma Barzman
    Norma Barzman was an American screenwriter and author associated with the Hollywood blacklist era and known for her political activism and memoirs.
  • C. Norma Anderson
    Norma Anderson was the first wife of acclaimed American actor Burt Lancaster, with whom she shared a long marriage and several children before their divorce.
  • D. Norma Varden
    Norma Varden was a British-born character actress known for her refined, often comedic supporting roles in mid-20th-century films such as "Casablanca" and "Gentlemen Prefer Blondes."
  • E. Norma Donaldson
    Norma Donaldson was an American actress best known for her work in theater and television, including roles in notable stage productions and TV series.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1972737c08190bd011776564c3861 completed April 29, 2026, 5:29 a.m.
Created at: April 17, 2026, 5:05 p.m.