Triple

T15231065
Position Surface form Disambiguated ID Type / Status
Subject STS-87 E364000 entity
Predicate crewMember P2094 FINISHED
Object Kevin R. Kregel E921261 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: Kevin R. Kregel | Statement: [STS-87, crewMember, Kevin R. Kregel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kevin R. Kregel
Context triple: [STS-87, crewMember, Kevin R. Kregel]
  • A. Kevin R. Kregel chosen
    Kevin R. Kregel is a former NASA astronaut and U.S. Air Force test pilot who flew on multiple Space Shuttle missions in the 1990s and early 2000s.
  • B. Michael B. Green
    Michael B. Green is a British theoretical physicist and pioneer of string theory, renowned for his foundational work on anomaly cancellation and the development of modern superstring theory.
  • C. M. William Bray
    M. William Bray was an American politician who served as the Democratic nominee for lieutenant governor of New York alongside Herbert H. Lehman in the early 1930s.
  • D. Bert J. Enger
    Bert J. Enger was a Duluth businessman and philanthropist whose legacy is commemorated by the landmark Enger Tower.
  • E. Michael J. Horton
    Michael J. Horton is a film editor best known for his work on major feature films, including serving on the editing team for "The Lord of the Rings: The Two Towers."
  • 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_69d85a0ce24c81909c4d3b6475548c95 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0078e27408190bc13c0ca441f5594 completed April 15, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd3beae88190a91af2c9a7def8f8 completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 3:12 a.m.