Triple

T5002165
Position Surface form Disambiguated ID Type / Status
Subject AS E112398 entity
Predicate airlineICAOCode P26821 FINISHED
Object ASA
ASA is the ICAO airline designator used to identify Alaska Airlines in international aviation operations.
E113918 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: ASA | Statement: [AS, airlineICAOCode, ASA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ASA
Context triple: [AS, airlineICAOCode, ASA]
  • A. ASA
    ASA is the commonly used abbreviation for the Academy of Sciences of Albania, the country’s leading scientific research and advisory institution.
  • B. ASA
    ASA is the acronym for Aeropuertos y Servicios Auxiliares, the Mexican government agency responsible for operating and managing numerous airports and providing auxiliary aviation services in Mexico.
  • C. ASA
    ASA is the acronym for the Australian Space Agency, the national body responsible for coordinating Australia’s civil space activities and industry growth.
  • D. ASA
    ASA is the commonly used abbreviation for the Acoustical Society of America, a leading scientific society dedicated to the study and advancement of acoustics.
  • E. ASA
    ASA is an abbreviation commonly used to refer to the Assistant Secretary of the Army, a senior civilian official in the United States Department of the Army responsible for high-level policy and oversight.
  • 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: ASA
Triple: [AS, airlineICAOCode, ASA]
Generated description
ASA is the ICAO airline designator used to identify Alaska Airlines in international aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ASA
Target entity description: ASA is the ICAO airline designator used to identify Alaska Airlines in international aviation operations.
  • A. ASA chosen
    ASA is the ICAO airline designator used to identify Alaska Airlines in international aviation operations and communications.
  • B. ASA
    ASA is the acronym for Aeropuertos y Servicios Auxiliares, the Mexican government agency responsible for operating and managing numerous airports and providing auxiliary aviation services in Mexico.
  • C. ASA
    ASA is the commonly used abbreviation for the Acoustical Society of America, a leading scientific society dedicated to the study and advancement of acoustics.
  • D. ASA
    ASA is the commonly used abbreviation for the Academy of Sciences of Albania, the country’s leading scientific research and advisory institution.
  • E. ASA
    ASA is the acronym for the Australian Space Agency, the national body responsible for coordinating Australia’s civil space activities and industry growth.
  • 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_69bd4433d0b08190877e83959ef40d81 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd72bf0de08190a07419514afc3a06 completed March 20, 2026, 4:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be92598ff88190b63a589524180272 completed March 21, 2026, 12:43 p.m.
NEDg Description generation batch_69be9323c5fc819084a4dbf59bab24cd completed March 21, 2026, 12:46 p.m.
NED2 Entity disambiguation (via description) batch_69be93bafdbc8190b7add3fbcc33a317 completed March 21, 2026, 12:48 p.m.
Created at: March 20, 2026, 1:34 p.m.