Triple

T7019072
Position Surface form Disambiguated ID Type / Status
Subject Kunming Changshui International Airport E162772 entity
Predicate IATAcode P418 FINISHED
Object KMG
KMG is the IATA airport code for Kunming Changshui International Airport, a major air transport hub serving Kunming in Yunnan Province, China.
 E637089 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: KMG | Statement: [Kunming Changshui International Airport, IATAcode, KMG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KMG
Context triple: [Kunming Changshui International Airport, IATAcode, KMG]
  • A. KMKG
    KMKG is the ICAO airport code for Muskegon County Airport in Muskegon, Michigan, United States.
  • B. KMK
    KMK is the central coordinating body of Germany’s state education and cultural ministers, responsible for harmonizing policies across the federal states.
  • C. KMA
    KMA is the commonly used abbreviation for the Royal Swedish Academy of Music, Sweden’s national institution dedicated to the advancement of musical art and scholarship.
  • D. KMGM
    KMGM is the ICAO airport code for Montgomery Regional Airport, a public airport serving Montgomery, Alabama.
  • E. KMC
    KMC is the commonly used abbreviation for Kirori Mal College, a prominent constituent college of the University of Delhi in India.
  • 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: KMG
Triple: [Kunming Changshui International Airport, IATAcode, KMG]
Generated description
KMG is the IATA airport code for Kunming Changshui International Airport, a major air transport hub serving Kunming in Yunnan Province, China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KMG
Target entity description: KMG is the IATA airport code for Kunming Changshui International Airport, a major air transport hub serving Kunming in Yunnan Province, China.
  • A. KMKG
    KMKG is the ICAO airport code for Muskegon County Airport in Muskegon, Michigan, United States.
  • B. KMK
    KMK is the central coordinating body of Germany’s state education and cultural ministers, responsible for harmonizing policies across the federal states.
  • C. KMA
    KMA is the commonly used abbreviation for the Royal Swedish Academy of Music, Sweden’s national institution dedicated to the advancement of musical art and scholarship.
  • D. KMGM
    KMGM is the ICAO airport code for Montgomery Regional Airport, a public airport serving Montgomery, Alabama.
  • E. KMC
    KMC is the commonly used abbreviation for Kirori Mal College, a prominent constituent college of the University of Delhi in India.
  • 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_69c6885a127c8190867b059bdccf13ff completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1e8e36c81908c95a8181781cda4 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7756a50608190b548ce4aeaaf9f9d completed March 28, 2026, 6:30 a.m.
NEDg Description generation batch_69c77814712881908d0754fd02514f94 completed March 28, 2026, 6:41 a.m.
NED2 Entity disambiguation (via description) batch_69c778f30b248190a4a02039de68b965 completed March 28, 2026, 6:45 a.m.
Created at: March 27, 2026, 2:34 p.m.