Triple

T8705459
Position Surface form Disambiguated ID Type / Status
Subject File 770 E206636 entity
Predicate creator P184 FINISHED
Object Mike Glyer E251158 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: Mike Glyer | Statement: [File 770, creator, Mike Glyer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Glyer
Context triple: [File 770, creator, Mike Glyer]
  • A. Mike Glyer chosen
    Mike Glyer is a prominent science fiction fan writer, editor, and fan historian best known for his long-running fanzine "File 770" and multiple Hugo Awards.
  • B. Michael Gaeta
    Michael Gaeta is a film producer best known for his work on genre movies, including the 2011 remake of the horror-comedy "Fright Night."
  • C. Matt Olmstead
    Matt Olmstead is an American television writer and producer best known for his work on crime and drama series such as "NYPD Blue," "Prison Break," and the "Chicago" franchise.
  • D. Mark Geiger
    Mark Geiger is a retired American soccer referee known for officiating at Major League Soccer’s highest levels and multiple FIFA World Cups.
  • E. Mike Viola
    Mike Viola is an American singer-songwriter, musician, and record producer known for his work on power pop and rock projects, including film soundtracks and albums by various acclaimed artists.
  • 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_69ca835645e881908f00e3c8b51da81d completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc58fb43f081909df5d1e31cb1ec04 completed March 31, 2026, 11:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf4287aa048190ba0263623d02b2ef completed April 3, 2026, 4:31 a.m.
Created at: March 30, 2026, 6:34 p.m.