Triple

T20543004
Position Surface form Disambiguated ID Type / Status
Subject Mir-NASA program E504393 entity
Predicate sentAstronaut P122385 FINISHED
Object John Blaha NE NERFINISHED

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 Blaha | Statement: [Mir-NASA program, sentAstronaut, John Blaha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Blaha
Context triple: [Mir-NASA program, sentAstronaut, John Blaha]
  • A. John Blaha chosen
    John Blaha is a retired NASA astronaut and former U.S. Air Force colonel who flew on multiple Space Shuttle missions and spent time aboard the Mir space station.
  • B. Michael Blaha
    Michael Blaha is a computer scientist and software engineer known for his pioneering work in object-oriented modeling and database design, including co-developing the Object Modeling Technique (OMT).
  • C. John Sikela
    John Sikela was a Golden Age comic book artist best known for his work on early Superman stories for DC Comics.
  • D. William Prochnau
    William Prochnau was an American journalist and author known for his in-depth reporting on war correspondents and international conflicts, several of whose works were adapted for film.
  • E. Jon Bosak
    Jon Bosak is a computer scientist best known for leading the original XML specification effort at the World Wide Web Consortium (W3C), which helped standardize data interchange on the web.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a293feac8190b27848b64f2db1fe completed April 20, 2026, 10:03 p.m.
Created at: April 16, 2026, 11:38 a.m.