Triple

T2422559
Position Surface form Disambiguated ID Type / Status
Subject Shenzhen Airlines E53450 entity
Predicate ICAOcode P419 FINISHED
Object CSZ
CSZ is the ICAO airline designator assigned to Shenzhen Airlines, a major Chinese carrier based in Shenzhen.
 E265119 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: CSZ | Statement: [Shenzhen Airlines, ICAOcode, CSZ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CSZ
Context triple: [Shenzhen Airlines, ICAOcode, CSZ]
  • A. CZI
    CZI is a philanthropic organization founded by Priscilla Chan and Mark Zuckerberg that focuses on advancing science, education, and social justice through technology-driven initiatives and grantmaking.
  • B. CZ
    CZ is the IATA airline designator assigned to China Southern Airlines, one of China’s largest carriers.
  • C. CZM
    CZM is the Massachusetts state agency responsible for protecting, managing, and enhancing the Commonwealth’s coastal resources and communities.
  • D. CSD
    CSD is the renowned Computer Science Department at Carnegie Mellon University, recognized globally for its pioneering research and education in computer science.
  • E. ZS
    ZS is the vehicle registration code assigned to cars registered in the Polish city of Szczecin.
  • 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: CSZ
Triple: [Shenzhen Airlines, ICAOcode, CSZ]
Generated description
CSZ is the ICAO airline designator assigned to Shenzhen Airlines, a major Chinese carrier based in Shenzhen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CSZ
Target entity description: CSZ is the ICAO airline designator assigned to Shenzhen Airlines, a major Chinese carrier based in Shenzhen.
  • A. CZI
    CZI is a philanthropic organization founded by Priscilla Chan and Mark Zuckerberg that focuses on advancing science, education, and social justice through technology-driven initiatives and grantmaking.
  • B. CZ
    CZ is the IATA airline designator assigned to China Southern Airlines, one of China’s largest carriers.
  • C. CZM
    CZM is the Massachusetts state agency responsible for protecting, managing, and enhancing the Commonwealth’s coastal resources and communities.
  • D. CSD
    CSD is the renowned Computer Science Department at Carnegie Mellon University, recognized globally for its pioneering research and education in computer science.
  • E. ZS
    ZS is the vehicle registration code assigned to cars registered in the Polish city of Szczecin.
  • 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_69ab495c44d48190b7235b23719bc3f6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc972934481909e05bd6f31162f9d completed March 7, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebf5b1bb8819095920d702c180d3f completed March 9, 2026, 12:38 p.m.
NEDg Description generation batch_69aec338adf481908492b99d6e949bf8 completed March 9, 2026, 12:55 p.m.
NED2 Entity disambiguation (via description) batch_69aec3d410048190b908e883442b4ac2 completed March 9, 2026, 12:57 p.m.
Created at: March 6, 2026, 9:42 p.m.