Triple

T16312614
Position Surface form Disambiguated ID Type / Status
Subject Bobby Shriver E396094 entity
Predicate relative P37 FINISHED
Object John F. Kennedy E305 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: John F. Kennedy | Statement: [Bobby Shriver, relative, John F. Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John F. Kennedy
Context triple: [Bobby Shriver, relative, John F. Kennedy]
  • A. John F. Kennedy chosen
    John F. Kennedy was the 35th president of the United States, known for his leadership during the Cold War, the Cuban Missile Crisis, and the early stages of the civil rights movement before his assassination in 1963.
  • B. John Kennedy
    John Kennedy is a film director known for his work on the movie "Up in Central Park."
  • C. Presidente Kennedy
    Presidente Kennedy is a small coastal municipality in the Brazilian state of Espírito Santo, known for its beaches and growing oil and gas-related economic activities.
  • D. JFK
    JFK is John F. Kennedy International Airport, a major international air travel hub serving New York City.
  • E. RJFK
    RJFK is the ICAO airport code for Kagoshima Airport, a regional and domestic aviation hub on Japan’s Kyushu island.
  • 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_69d87f23bb088190a16fbb91a1957ea5 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e288dc30f48190b508220429b66e92 completed April 17, 2026, 7:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a002da444408190b770055d84060f4d completed May 10, 2026, 7:03 a.m.
Created at: April 10, 2026, 5:06 a.m.