Triple

T7490716
Position Surface form Disambiguated ID Type / Status
Subject Chiang Mai International Airport E176997 entity
Predicate IATAcode P418 FINISHED
Object CNX
CNX is the IATA airport code for Chiang Mai International Airport, the main air gateway to northern Thailand.
 E668774 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: CNX | Statement: [Chiang Mai International Airport, IATAcode, CNX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CNX
Context triple: [Chiang Mai International Airport, IATAcode, CNX]
  • A. CNX
    CNX was a short-lived UK digital television channel from Cartoon Network that targeted older teens and young adults with action-oriented and anime programming.
  • B. CNK
    CNK is the stock ticker symbol for Cinemark Holdings, Inc., a major American movie theater chain operator.
  • C. CNCS
    CNCS is a French national museum dedicated to preserving and showcasing theatrical, opera, and ballet costumes and stage sets.
  • D. CNCS
    CNCS is the abbreviation for the Corporation for National and Community Service, the U.S. federal agency that supports national service programs like AmeriCorps and Senior Corps.
  • E. CNU
    CNU is a major national research university located in Daejeon, South Korea, known for its comprehensive academic programs and strong emphasis on science and technology.
  • 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: CNX
Triple: [Chiang Mai International Airport, IATAcode, CNX]
Generated description
CNX is the IATA airport code for Chiang Mai International Airport, the main air gateway to northern Thailand.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CNX
Target entity description: CNX is the IATA airport code for Chiang Mai International Airport, the main air gateway to northern Thailand.
  • A. CNX
    CNX was a short-lived UK digital television channel from Cartoon Network that targeted older teens and young adults with action-oriented and anime programming.
  • B. CNK
    CNK is the stock ticker symbol for Cinemark Holdings, Inc., a major American movie theater chain operator.
  • C. CNCS
    CNCS is a French national museum dedicated to preserving and showcasing theatrical, opera, and ballet costumes and stage sets.
  • D. CNCS
    CNCS is the abbreviation for the Corporation for National and Community Service, the U.S. federal agency that supports national service programs like AmeriCorps and Senior Corps.
  • E. CNU
    CNU is a major national research university located in Daejeon, South Korea, known for its comprehensive academic programs and strong emphasis on science and technology.
  • 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_69c69f2583808190bd1a4936c42a5815 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f55bdb3481908653b46eafba011d completed March 27, 2026, 9:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83c76a8988190bb5ff21731b19d4b completed March 28, 2026, 8:39 p.m.
NEDg Description generation batch_69c83e4052b481908df2fc43c71b3b07 completed March 28, 2026, 8:46 p.m.
NED2 Entity disambiguation (via description) batch_69c83ed33870819094b085229376da8a completed March 28, 2026, 8:49 p.m.
Created at: March 27, 2026, 3:43 p.m.