Triple

T2422540
Position Surface form Disambiguated ID Type / Status
Subject TAP Air Portugal E53449 entity
Predicate hasSubsidiary P254 FINISHED
Object TAP Express
TAP Express is a regional airline brand operating feeder and short-haul services on behalf of TAP Air Portugal.
E265117 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: TAP Express | Statement: [TAP Air Portugal, hasSubsidiary, TAP Express]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TAP Express
Context triple: [TAP Air Portugal, hasSubsidiary, TAP Express]
  • A. ATA Airlines
    ATA Airlines is an Iranian airline that operates domestic and regional flights, using Mehrabad International Airport in Tehran as one of its main bases.
  • B. Flynas
    Flynas is a Saudi low-cost airline based in Riyadh that operates domestic and regional flights across the Middle East and beyond.
  • C. TUI Airways
    TUI Airways is a British charter and scheduled airline that primarily serves leisure destinations across Europe and worldwide as part of the TUI Group.
  • D. Crossair
    Crossair was a former Swiss regional airline that served as the main predecessor to Swiss International Air Lines after the collapse of Swissair.
  • E. Flair Airlines
    Flair Airlines is a Canadian ultra-low-cost carrier that operates domestic and select international flights, emphasizing budget-friendly travel options.
  • 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: TAP Express
Triple: [TAP Air Portugal, hasSubsidiary, TAP Express]
Generated description
TAP Express is a regional airline brand operating feeder and short-haul services on behalf of TAP Air Portugal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TAP Express
Target entity description: TAP Express is a regional airline brand operating feeder and short-haul services on behalf of TAP Air Portugal.
  • A. ATA Airlines
    ATA Airlines is an Iranian airline that operates domestic and regional flights, using Mehrabad International Airport in Tehran as one of its main bases.
  • B. Flynas
    Flynas is a Saudi low-cost airline based in Riyadh that operates domestic and regional flights across the Middle East and beyond.
  • C. TUI Airways
    TUI Airways is a British charter and scheduled airline that primarily serves leisure destinations across Europe and worldwide as part of the TUI Group.
  • D. Crossair
    Crossair was a former Swiss regional airline that served as the main predecessor to Swiss International Air Lines after the collapse of Swissair.
  • E. Flair Airlines
    Flair Airlines is a Canadian ultra-low-cost carrier that operates domestic and select international flights, emphasizing budget-friendly travel options.
  • 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.