Triple

T10813026
Position Surface form Disambiguated ID Type / Status
Subject Ella Lorena Kennedy E255149 entity
Predicate relative P37 FINISHED
Object Frank Kennedy E891541 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: Frank Kennedy | Statement: [Ella Lorena Kennedy, relative, Frank Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Kennedy
Context triple: [Ella Lorena Kennedy, relative, Frank Kennedy]
  • A. Frank Kennedy
    Frank Kennedy is a character in Margaret Mitchell's novel "Gone with the Wind," known as a middle-aged Atlanta businessman who marries Scarlett O'Hara for practical reasons.
  • B. Frank Kennedy chosen
    Frank Kennedy is the father of Ella Lorena Kennedy, about whom little widely known public information is available.
  • C. James Kennedy
    James Kennedy was a 15th-century Scottish bishop and statesman who served as Bishop of St Andrews and played a key role in the political and ecclesiastical life of medieval Scotland.
  • D. Thomas Francis Kennedy
    Thomas Francis Kennedy was a 19th-century Scottish Whig politician and reformer closely associated with leading liberal figures of his time.
  • E. John Fitzgerald
    John Fitzgerald is the founder of the global financial services firm Cantor Fitzgerald.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733eba9b48190b4dbe7fe5d8be0a4 completed April 9, 2026, 5:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69e21649a6308190878432635d523686 completed April 17, 2026, 11:15 a.m.
Created at: April 8, 2026, 9:18 p.m.