Triple

T9877828
Position Surface form Disambiguated ID Type / Status
Subject Kalamazoo/Battle Creek International Airport E240117 entity
Predicate ICAOcode P419 FINISHED
Object KAZO
KAZO is the ICAO airport code for Kalamazoo/Battle Creek International Airport in Michigan, United States.
E826568 NE FINISHED

How this triple was built (4 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: KAZO | Statement: [Kalamazoo/Battle Creek International Airport, ICAOcode, KAZO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KAZO
Context triple: [Kalamazoo/Battle Creek International Airport, ICAOcode, KAZO]
  • A. KAZ
    KAZ is the three-letter ISO 3166-1 alpha-3 country code assigned to Kazakhstan for international standardization and identification.
  • B. KZ
    KZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Kazakhstan for international standardization and identification.
  • C. Kaz
    Kaz is a central protagonist in the Disney XD series "Mighty Med," known as a comic book fan who becomes a sidekick and caretaker to real-life superheroes.
  • D. Kaz
    Kaz is one of the futuristic, computer-generated Spheriks characters that served as an official mascot for the 2002 FIFA World Cup in South Korea and Japan.
  • E. Kaz
    Kaz is a person known for working closely with Nik as a teammate, likely in a collaborative or competitive setting such as sports, gaming, or a professional project.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KAZO
Triple: [Kalamazoo/Battle Creek International Airport, ICAOcode, KAZO]
Generated description
KAZO is the ICAO airport code for Kalamazoo/Battle Creek International Airport in Michigan, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KAZO
Target entity description: KAZO is the ICAO airport code for Kalamazoo/Battle Creek International Airport in Michigan, United States.
  • A. KAZ
    KAZ is the three-letter ISO 3166-1 alpha-3 country code assigned to Kazakhstan for international standardization and identification.
  • B. KZ
    KZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Kazakhstan for international standardization and identification.
  • C. Kaz
    Kaz is one of the futuristic, computer-generated Spheriks characters that served as an official mascot for the 2002 FIFA World Cup in South Korea and Japan.
  • D. Kaz
    Kaz is a central protagonist in the Disney XD series "Mighty Med," known as a comic book fan who becomes a sidekick and caretaker to real-life superheroes.
  • E. Kaz
    Kaz is a person known for working closely with Nik as a teammate, likely in a collaborative or competitive setting such as sports, gaming, or a professional project.
  • F. None of above. chosen

Provenance (5 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_69ca84e8a0788190b9061811d50fd554 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb411fc78819082c52ae4233a6550 completed April 2, 2026, 12:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1e480ead08190992eb43ea3eac38b completed April 5, 2026, 4:26 a.m.
NEDg Description generation batch_69d1e5d0da7081908e14fe4bc6623ea5 completed April 5, 2026, 4:32 a.m.
NED2 Entity disambiguation (via description) batch_69d1e6af89f88190abe63f8172182f58 completed April 5, 2026, 4:35 a.m.
Created at: March 30, 2026, 8:37 p.m.