Triple

T17946748
Position Surface form Disambiguated ID Type / Status
Subject David Read E448721 entity
Predicate relative P37 FINISHED
Object Grandma Thora Read 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: Grandma Thora Read | Statement: [David Read, relative, Grandma Thora Read]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grandma Thora Read
Context triple: [David Read, relative, Grandma Thora Read]
  • A. Grandma Thora Read chosen
    Grandma Thora Read is Arthur Read’s kind, elderly grandmother in the "Arthur" children’s book and animated TV series, known for her warmth, wisdom, and close relationship with her grandchildren.
  • B. Dorothy Trosper
    Dorothy Trosper was the wife of American screenwriter and producer Guy Trosper.
  • C. Dorothy Duffy
    Dorothy Duffy is an Irish actress best known for her role in the film "The Magdalene Sisters."
  • D. Enid Anne Loftis
    Enid Anne Loftis was the wife of American character actor Morgan Woodward.
  • E. Dorothy Squires
    Dorothy Squires was a Welsh singer known for her powerful voice and dramatic torch songs, who enjoyed significant popularity in the mid-20th century.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad99df408190a8a4e3d21c03fe71 completed April 19, 2026, 10:25 a.m.
Created at: April 10, 2026, 10:21 a.m.