Triple

T8151208
Position Surface form Disambiguated ID Type / Status
Subject Oliver Stone E190336 entity
Predicate directed P7373 FINISHED
Object JFK 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: JFK | Statement: [Oliver Stone, directed, JFK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: JFK
Context triple: [Oliver Stone, directed, JFK]
  • A. JFK
    JFK is John F. Kennedy International Airport, a major international air travel hub serving New York City.
  • B. 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.
  • C. RJFK
    RJFK is the ICAO airport code for Kagoshima Airport, a regional and domestic aviation hub on Japan’s Kyushu island.
  • D. Kennedy
    Kennedy is a vast rural federal electoral division in Queensland, Australia, known for encompassing remote outback communities and mining towns.
  • E. Kennedy
    Kennedy is a prominent Irish-American political and public-service family best known for producing U.S. President John F. Kennedy and numerous other influential politicians.
  • 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_69ca82be7ba8819087de0147e9292c83 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4483799c81908e73f9a87ed99185 completed March 31, 2026, 3:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69cced3839b4819081a811fcebc51ff7 completed April 1, 2026, 10:02 a.m.
Created at: March 30, 2026, 5:37 p.m.