Triple

T14156603
Position Surface form Disambiguated ID Type / Status
Subject John Compton E350829 entity
Predicate name P16 FINISHED
Object John Compton E350829 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 Compton | Statement: [John Compton, name, John Compton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Compton
Context triple: [John Compton, name, John Compton]
  • A. John Compton chosen
    John Compton was a Saint Lucian statesman who led the country to independence and served multiple terms as its prime minister.
  • B. Bill Compton
    Bill Compton is a centuries-old vampire and central protagonist in the television series "True Blood," known for his complex morality and romantic relationship with Sookie Stackhouse.
  • C. Patrick Compton
    Patrick Compton is an individual notable enough to be recognized as a prominent bearer of the surname Compton.
  • D. Dennis Higgs
    Dennis Higgs is a biologist known for his research in molecular evolution and his work as a professor at the University of Windsor.
  • E. John McKinley
    John McKinley was an Associate Justice of the U.S. Supreme Court in the mid-19th century, known for his participation in significant cases involving federal power and economic development.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6135744c81909a43d659f5fe2895 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7ec6448819087e50aac964ec637 completed May 7, 2026, 8:37 p.m.
Created at: April 10, 2026, 12:58 a.m.