Triple

T18900715
Position Surface form Disambiguated ID Type / Status
Subject Ian Ballantine E462332 entity
Predicate partnerInBusinessWith P282 FINISHED
Object Betty Ballantine 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: Betty Ballantine | Statement: [Ian Ballantine, partnerInBusinessWith, Betty Ballantine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betty Ballantine
Context triple: [Ian Ballantine, partnerInBusinessWith, Betty Ballantine]
  • A. Betty Ballantine chosen
    Betty Ballantine was a pioneering American publisher and editor who helped popularize mass-market paperbacks and co-founded the influential imprint Ballantine Books.
  • B. Margaret Huston
    Margaret Huston is known primarily as the wife of James Ramsay.
  • C. Barbara Mallery
    Barbara Mallery was the first wife of American television and radio personality Dick Clark, whom he married early in his career.
  • D. Judith Hoag
    Judith Hoag is an American actress best known for her roles in the original Teenage Mutant Ninja Turtles film and Disney Channel’s Halloweentown series.
  • E. Barbara Follett
    Barbara Follett is a British Labour politician and former Member of Parliament who served as a government minister under Prime Minister Gordon Brown.
  • 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_69d8dcfd05bc819088903cca13cc2846 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c5289ba48190a6825c4db2e5e48d completed April 20, 2026, 6:18 a.m.
Created at: April 10, 2026, 11:58 a.m.