Triple

T9281790
Position Surface form Disambiguated ID Type / Status
Subject Ellen Griswold E223084 entity
Predicate hasRelative P367 FINISHED
Object Catherine Johnson E804691 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: Catherine Johnson | Statement: [Ellen Griswold, hasRelative, Catherine Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catherine Johnson
Context triple: [Ellen Griswold, hasRelative, Catherine Johnson]
  • A. Catherine Johnson chosen
    Catherine Johnson is a fictional character from the 1989 comedy film "National Lampoon’s Christmas Vacation," which follows the chaotic holiday misadventures of the Griswold family.
  • B. Catherine Johnson
    Catherine Johnson is a creator or author known for her work associated with Bill Anderson.
  • C. Catherine Nuth Johnson
    Catherine Nuth Johnson was the mother of Louisa Catherine Adams, who became First Lady of the United States as the wife of President John Quincy Adams.
  • D. Anna Boyd
    Anna Boyd is a character associated with Rachel Watson, likely appearing as one of her allies in the psychological thriller novel and film "The Girl on the Train."
  • E. Elouise Sidwell
    Elouise Sidwell was the wife of American composer and television theme music writer Earle Hagen.
  • 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_69ca842123588190b3f2e1a69037d141 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd081c2b048190aa6930de3bf2f87f completed April 1, 2026, 11:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1525bd4e88190a62e5e383d1e786b completed April 4, 2026, 6:03 p.m.
Created at: March 30, 2026, 7:34 p.m.