Triple

T1640728
Position Surface form Disambiguated ID Type / Status
Subject Haneda Airport E35463 entity
Predicate focusCityFor P164 FINISHED
Object StarFlyer
StarFlyer is a Japanese airline known for its stylish black-themed aircraft and service-focused operations on domestic routes.
 E186918 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: StarFlyer | Statement: [Haneda Airport, focusCityFor, StarFlyer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: StarFlyer
Context triple: [Haneda Airport, focusCityFor, StarFlyer]
  • A. Nordwind Airlines
    Nordwind Airlines is a Russian leisure and charter airline that primarily operates holiday and tourist flights from major hubs such as Moscow.
  • B. Flying J Inc.
    Flying J Inc. was a major American truck stop and travel center chain that later became part of the Pilot Flying J network.
  • C. All Star Cafe
    All Star Cafe was a themed sports restaurant chain backed by prominent athletes and media partners that operated in the late 1990s and early 2000s.
  • D. Sabre
    Sabre is a leading global travel technology company that provides software and distribution solutions for airlines, hotels, and travel agencies.
  • E. Sharchop
    The Sharchop are an indigenous ethnic group of eastern Bhutan known for their distinct Tibeto-Burman language varieties and cultural traditions.
  • 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: StarFlyer
Triple: [Haneda Airport, focusCityFor, StarFlyer]
Generated description
StarFlyer is a Japanese airline known for its stylish black-themed aircraft and service-focused operations on domestic routes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: StarFlyer
Target entity description: StarFlyer is a Japanese airline known for its stylish black-themed aircraft and service-focused operations on domestic routes.
  • A. Nordwind Airlines
    Nordwind Airlines is a Russian leisure and charter airline that primarily operates holiday and tourist flights from major hubs such as Moscow.
  • B. Flying J Inc.
    Flying J Inc. was a major American truck stop and travel center chain that later became part of the Pilot Flying J network.
  • C. All Star Cafe
    All Star Cafe was a themed sports restaurant chain backed by prominent athletes and media partners that operated in the late 1990s and early 2000s.
  • D. Sabre
    Sabre is a leading global travel technology company that provides software and distribution solutions for airlines, hotels, and travel agencies.
  • E. Sharchop
    The Sharchop are an indigenous ethnic group of eastern Bhutan known for their distinct Tibeto-Burman language varieties and cultural traditions.
  • 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_69a88604618c81908b41f6429c431eb6 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90a3c883c8190bec1d87ecedf2575 completed March 5, 2026, 4:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad609cf8488190ba334bdff2c5e78d completed March 8, 2026, 11:42 a.m.
NEDg Description generation batch_69ad61ff65b881909009c230780a146e completed March 8, 2026, 11:48 a.m.
NED2 Entity disambiguation (via description) batch_69ad62ec3a80819085fef1c378b9abdc completed March 8, 2026, 11:52 a.m.
Created at: March 4, 2026, 7:28 p.m.