Triple

T10753139
Position Surface form Disambiguated ID Type / Status
Subject Singapore–New York (ultra-long-haul) E253620 entity
Predicate servedByFlightNumber P67178 FINISHED
Object SQ23
SQ23 is Singapore Airlines’ flagship ultra-long-haul nonstop flight operating between Singapore and New York.
 E253609 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: SQ23 | Statement: [Singapore–New York (ultra-long-haul), servedByFlightNumber, SQ23]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SQ23
Context triple: [Singapore–New York (ultra-long-haul), servedByFlightNumber, SQ23]
  • A. SQ3
    SQ3 is a designated quadrant within the Southern Cross region, used for organizing and referencing a specific area of the sky.
  • B. S-23
    S-23 is an International Hydrographic Organization publication that standardizes the naming and limits of the world’s oceans and seas.
  • C. SQ
    SQ is the IATA airline designator used worldwide to identify Singapore Airlines on tickets, timetables, and flight numbers.
  • D. SQ
    SQ is the commonly used abbreviation for Stadiums Queensland, the government agency responsible for managing major sports and entertainment venues in Queensland, Australia.
  • E. SQ
    SQ is the stock ticker symbol for Block, Inc. (formerly Square, Inc.), a major American financial technology company known for its payment processing and digital financial services.
  • 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: SQ23
Triple: [Singapore–New York (ultra-long-haul), servedByFlightNumber, SQ23]
Generated description
SQ23 is Singapore Airlines’ flagship ultra-long-haul nonstop flight operating between Singapore and New York.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SQ23
Target entity description: SQ23 is Singapore Airlines’ flagship ultra-long-haul nonstop flight operating between Singapore and New York.
  • A. SQ3
    SQ3 is a designated quadrant within the Southern Cross region, used for organizing and referencing a specific area of the sky.
  • B. S-23
    S-23 is an International Hydrographic Organization publication that standardizes the naming and limits of the world’s oceans and seas.
  • C. SQ chosen
    SQ is the IATA airline designator used worldwide to identify Singapore Airlines on tickets, timetables, and flight numbers.
  • D. SQ
    SQ is the commonly used abbreviation for Stadiums Queensland, the government agency responsible for managing major sports and entertainment venues in Queensland, Australia.
  • E. SQ
    SQ is the stock ticker symbol for Block, Inc. (formerly Square, Inc.), a major American financial technology company known for its payment processing and digital financial services.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d71dc2543c8190bb060aa7a1fed6a6 completed April 9, 2026, 3:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69dbdb897f7c81909002f2478613eff8 completed April 12, 2026, 5:51 p.m.
NEDg Description generation batch_69dd4367104c8190b83a7877be011b11 completed April 13, 2026, 7:26 p.m.
NED2 Entity disambiguation (via description) batch_69de01eae1bc819092dcd48328eea943 completed April 14, 2026, 8:59 a.m.
Created at: April 8, 2026, 9:15 p.m.