Triple

T8222738
Position Surface form Disambiguated ID Type / Status
Subject Shanghai Airlines E192102 entity
Predicate ICAOcode P419 FINISHED
Object CSH
CSH is the ICAO airline designator used to identify Shanghai Airlines in international aviation operations.
 E719229 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: CSH | Statement: [Shanghai Airlines, ICAOcode, CSH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CSH
Context triple: [Shanghai Airlines, ICAOcode, CSH]
  • A. CSH
    CSH is an abbreviation commonly used for the College of Science and Health, an academic division focused on scientific and health-related disciplines.
  • B. CHS
    CHS is the abbreviation for the Committee on Hemispheric Security, a body within the Organization of American States focused on security issues in the Western Hemisphere.
  • C. CHS
    CHS is the three-letter IATA airport code for Charleston International Airport, the primary commercial airport serving the Charleston, South Carolina area.
  • D. CHS
    CHS is the abbreviation for the Council of Heads of State, a high-level political body composed of the top leaders of member countries.
  • E. CSZ
    CSZ is the ICAO airline designator assigned to Shenzhen Airlines, a major Chinese carrier based in Shenzhen.
  • 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: CSH
Triple: [Shanghai Airlines, ICAOcode, CSH]
Generated description
CSH is the ICAO airline designator used to identify Shanghai Airlines in international aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CSH
Target entity description: CSH is the ICAO airline designator used to identify Shanghai Airlines in international aviation operations.
  • A. CSH
    CSH is an abbreviation commonly used for the College of Science and Health, an academic division focused on scientific and health-related disciplines.
  • B. CHS
    CHS is the abbreviation for the Committee on Hemispheric Security, a body within the Organization of American States focused on security issues in the Western Hemisphere.
  • C. CHS
    CHS is the three-letter IATA airport code for Charleston International Airport, the primary commercial airport serving the Charleston, South Carolina area.
  • D. CHS
    CHS is the abbreviation for the Council of Heads of State, a high-level political body composed of the top leaders of member countries.
  • E. CSZ
    CSZ is the ICAO airline designator assigned to Shenzhen Airlines, a major Chinese carrier based in Shenzhen.
  • 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_69ca82c9a8ac81908b011c38698456e4 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb77cae2948190ae4507b75b5d5784 completed March 31, 2026, 7:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccee09ac548190a9988ff77d43e77e completed April 1, 2026, 10:06 a.m.
NEDg Description generation batch_69ccf1bc720081908c4eabf58336318a completed April 1, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_69cd05eaba1c81908510a20b1ca93821 completed April 1, 2026, 11:47 a.m.
Created at: March 30, 2026, 5:45 p.m.