Triple

T20772578
Position Surface form Disambiguated ID Type / Status
Subject Rochester Monroe County Airport E511272 entity
Predicate hasICAOCode P419 FINISHED
Object KROC 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: KROC | Statement: [Rochester Monroe County Airport, hasICAOCode, KROC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KROC
Context triple: [Rochester Monroe County Airport, hasICAOCode, KROC]
  • A. KROC chosen
    KROC is the ICAO airport code for Frederick Douglass Greater Rochester International Airport, the primary commercial airport serving the Rochester, New York region.
  • B. Kro
    Kro is a powerful Deviant warlord and recurring Marvel Comics supervillain who frequently clashes with the Eternals.
  • C. Kroc
    Kroc is a surname most famously associated with Ray Kroc, the American businessman who built McDonald's into a global fast-food empire.
  • D. Krosp
    Krosp is a talking, genetically engineered cat and would-be Emperor of All Cats from the steampunk webcomic series "Girl Genius."
  • E. Kroft
    Kroft is a surname most notably associated with American journalist and longtime 60 Minutes correspondent Steve Kroft.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2681ff88190bfe5938c2db6b2c4 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.