Triple

T11683799
Position Surface form Disambiguated ID Type / Status
Subject STS-81 E277685 entity
Predicate missionSpecialist P21471 FINISHED
Object Peter J. K. Wisoff E922369 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: Peter J. K. Wisoff | Statement: [STS-81, missionSpecialist, Peter J. K. Wisoff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter J. K. Wisoff
Context triple: [STS-81, missionSpecialist, Peter J. K. Wisoff]
  • A. Peter J.K. Wisoff chosen
    Peter J.K. Wisoff is an American physicist and former NASA astronaut who flew on multiple Space Shuttle missions to help assemble and service the International Space Station.
  • B. Michele J. Wolff
    Michele J. Wolff is a screenwriter best known for her work on the film adaptation of the fantasy novel "Ella Enchanted."
  • C. Peter J. Weber
    Peter J. Weber was an architect known for his work on the annex of Chicago’s historic Fisher Building.
  • D. David N. Weiss
    David N. Weiss is an American screenwriter best known for co-writing popular family and animated films such as "Shrek 2" and "The Smurfs."
  • E. Peter S. Fischer
    Peter S. Fischer is an American television writer and producer best known for co-creating and writing numerous episodes of the mystery series "Murder, She Wrote."
  • 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_69d6aafe02d881909900d54ad7d4af84 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a463f6448190a4c8e1651a2bd905 completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69f417302ffc81908d222c4e01fa3e95 completed May 1, 2026, 3 a.m.
Created at: April 8, 2026, 9:40 p.m.