Triple

T10412464
Position Surface form Disambiguated ID Type / Status
Subject Air China E245425 entity
Predicate IATACode P418 FINISHED
Object CA
CA is the IATA airline designator assigned to Air China, the flag carrier of the People's Republic of China.
 E245422 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: CA | Statement: [Air China, IATACode, CA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CA
Context triple: [Air China, IATACode, CA]
  • A. CA
    CA is the vehicle registration code used on license plates for the Italian city of Cagliari.
  • B. CA
    CA is the commonly used abbreviation for Club Africain, a major Tunisian multi-sport club best known for its football team based in Tunis.
  • C. CA
    CA is the official abbreviation used for the professional head of the Australian Army.
  • D. CA
    CA is the abbreviated name for the Council of Administration, one of the main governing bodies of the Universal Postal Union responsible for overseeing its operations and policy implementation.
  • E. CA
    CA is the abbreviation for the Canadian Alliance, a former federal political party in Canada that existed from 2000 to 2003 and later merged into the Conservative Party of Canada.
  • 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: CA
Triple: [Air China, IATACode, CA]
Generated description
CA is the IATA airline designator assigned to Air China, the flag carrier of the People's Republic of China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CA
Target entity description: CA is the IATA airline designator assigned to Air China, the flag carrier of the People's Republic of China.
  • A. CA chosen
    CA is the IATA airline designator assigned to Air China, the flag carrier of the People's Republic of China.
  • B. CA
    CA is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Canada in international standards and systems.
  • C. CA
    CA is the vehicle registration code used on license plates for the Italian city of Cagliari.
  • D. CA
    CA is the abbreviated name for the Council of Administration, one of the main governing bodies of the Universal Postal Union responsible for overseeing its operations and policy implementation.
  • E. CA
    CA is the two-letter U.S. postal abbreviation for the state of California.
  • F. None of above.

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_69d381be340c8190b05998703d42d224 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea0e17f081908fb16425f65e5808 completed April 7, 2026, 11:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7fbfae96c8190ac496e9a1158afe4 completed April 9, 2026, 7:20 p.m.
NEDg Description generation batch_69d822d6a0188190a7ee6de5aab50486 completed April 9, 2026, 10:06 p.m.
NED2 Entity disambiguation (via description) batch_69d859e40bf88190a6dc8deed3049d31 completed April 10, 2026, 2:01 a.m.
Created at: April 6, 2026, 12:10 p.m.