Triple

T7950595
Position Surface form Disambiguated ID Type / Status
Subject Deep Blue Sea E184603 entity
Predicate storyBy P1955 FINISHED
Object Duncan Kennedy E710922 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: Duncan Kennedy | Statement: [Deep Blue Sea, storyBy, Duncan Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duncan Kennedy
Context triple: [Deep Blue Sea, storyBy, Duncan Kennedy]
  • A. Duncan Kennedy chosen
    Duncan Kennedy is a screenwriter best known for co-writing the 1999 science fiction horror film "Deep Blue Sea."
  • B. David A. Kennedy
    David A. Kennedy was an American member of the Kennedy family whose life was marked by personal struggles and a tragic early death from a drug overdose.
  • C. Francis Boyle
    Francis Boyle is a prominent American human rights lawyer and law professor known for his work in international law and advocacy for oppressed peoples.
  • D. David M. Kennedy
    David M. Kennedy is an American historian and Stanford University professor renowned for his influential works on U.S. history, particularly the Great Depression and World War II.
  • E. Karl Llewellyn
    Karl Llewellyn was a prominent 20th-century American legal scholar and leading figure of the legal realism movement, known especially for his role in drafting the Uniform Commercial Code.
  • 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_69ca8292cba881908a64427b938dac47 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3b5b7450819091e4e6f21e9d832d completed March 31, 2026, 3:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc937e687081908ae33ae7335d685e completed April 1, 2026, 3:39 a.m.
Created at: March 30, 2026, 5:10 p.m.