Triple

T16435128
Position Surface form Disambiguated ID Type / Status
Subject George Kennedy E399162 entity
Predicate notableWork P4 FINISHED
Object Airport 1975 E185797 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: Airport 1975 | Statement: [George Kennedy, notableWork, Airport 1975]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Airport 1975
Context triple: [George Kennedy, notableWork, Airport 1975]
  • A. Airport 1975 chosen
    Airport 1975 is a 1974 American disaster film and sequel in the Airport series, best known for its midair collision plot and ensemble cast.
  • B. Airport (1970 film)
    Airport (1970 film) is an American disaster-drama movie that follows the escalating crises at a snowbound Midwestern airport, helping launch the 1970s disaster film genre and inspiring several sequels.
  • C. Airport ’77
    Airport ’77 is a 1977 American disaster film in the Airport franchise, centered on a luxury jet that crashes into the ocean and becomes trapped underwater.
  • D. Flight ’76
    Flight ’76 is a disco-era musical work by Walter Murphy, best known as the follow-up to his hit orchestral-disco adaptation "A Fifth of Beethoven."
  • E. Airplane!
    Airplane! is a 1980 satirical disaster-comedy film that parodies the conventions of airline and disaster movies with rapid-fire visual gags and deadpan humor.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba1023481909588aa6a3c677886 completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0045872a688190bcab27c6a2b952cd completed May 10, 2026, 8:44 a.m.
Created at: April 10, 2026, 5:10 a.m.