Triple

T22957502
Position Surface form Disambiguated ID Type / Status
Subject Catherine Martin E570800 entity
Predicate relative P37 FINISHED
Object Ruth Martin 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: Ruth Martin | Statement: [Catherine Martin, relative, Ruth Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Martin
Context triple: [Catherine Martin, relative, Ruth Martin]
  • A. Ruth Martin chosen
    Ruth Martin is a fictional character from the soap opera "All My Children," known as a matriarchal figure in the Martin family.
  • B. Ruth Donnelly
    Ruth Donnelly was an American character actress known for her sharp-tongued, comedic supporting roles in numerous Hollywood films of the 1930s and 1940s.
  • C. Helen Fahey
    Helen Fahey is a central supporting character in the crime drama miniseries "Mare of Easttown," known as the sharp-tongued, opinionated mother of the protagonist, Mare Sheehan.
  • D. Janine Birkett
    Janine Birkett is an English actress best known for her role in the film "Billy Elliot."
  • E. Lucinda Coxon
    Lucinda Coxon is a British playwright and screenwriter known for her work on films such as "The Danish Girl" and various stage adaptations.
  • 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_69e245b212a88190b5259caf51606084 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181f21e588190a5a88a15c1b55dea completed April 29, 2026, 3:58 a.m.
Created at: April 17, 2026, 3:47 p.m.