Triple

T12086705
Position Surface form Disambiguated ID Type / Status
Subject Margaret Holland E287823 entity
Predicate sibling P363 FINISHED
Object Joan Holland E396613 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: Joan Holland | Statement: [Margaret Holland, sibling, Joan Holland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan Holland
Context triple: [Margaret Holland, sibling, Joan Holland]
  • A. Joan Holland chosen
    Joan Holland was an English noblewoman of the late 14th and early 15th centuries, connected to the royal House of York through her marriage to Edmund of Langley, 1st Duke of York.
  • B. Barbara Holland
    Barbara Holland is a minor but beloved character from the Netflix series "Stranger Things," known as Nancy Wheeler’s loyal best friend whose mysterious disappearance becomes an early catalyst for the show's supernatural events.
  • C. Joanna Holland
    Joanna Holland is an American former model best known as the third wife of television host Johnny Carson.
  • D. Joan Browne
    Joan Browne was the wife of American actor and singer Robert Alda.
  • E. Kathleen Gawthrop
    Kathleen Gawthrop is best known as the second wife of legendary American golfer Arnold Palmer.
  • 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_69d6ab4964708190850585628b287b0c completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d91514c78c8190bc1cd569e524e8b4 completed April 10, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f668eff88190877ce9bb991c1258 completed May 2, 2026, 1:04 p.m.
Created at: April 8, 2026, 9:48 p.m.