Triple

T3155665
Position Surface form Disambiguated ID Type / Status
Subject Air France-KLM E65978 entity
Predicate operatesLoyaltyProgram P13356 FINISHED
Object Flying Blue E93839 NE FINISHED

How this triple was built (3 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: Flying Blue | Statement: [Air France-KLM, operatesLoyaltyProgram, Flying Blue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flying Blue
Context triple: [Air France-KLM, operatesLoyaltyProgram, Flying Blue]
  • A. Flying Blue chosen
    Flying Blue is the joint frequent flyer loyalty program of Air France–KLM and partner airlines, offering members miles, elite status levels, and travel-related rewards.
  • B. Blue Air
    Blue Air is a Romanian low-cost airline that operated scheduled passenger flights across Europe.
  • C. Flying Finn
    Flying Finn is the famous nickname of Finnish middle- and long-distance runner Paavo Nurmi, one of the most dominant athletes in Olympic history.
  • D. Airblue
    Airblue is a Pakistani low-cost airline that operates domestic and international flights, with a primary base at Jinnah International Airport in Karachi.
  • E. Delta One
    Delta One is Delta Air Lines’ flagship international business-class cabin, featuring lie-flat seats, premium dining, and enhanced amenities for long-haul travelers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: operatesLoyaltyProgram
Context triple: [Air France-KLM, operatesLoyaltyProgram, Flying Blue]
  • A. supportsLoyaltyCards
    Indicates that an entity provides functionality to accept, manage, or work with loyalty cards for rewards or benefits.
  • B. loyaltyProgramType
    Indicates the specific category or kind of loyalty program associated with an entity (such as points-based, tiered, or subscription-based).
  • C. hasMembershipProgram chosen
    Indicates that an entity offers or participates in a structured membership program, typically providing special access, benefits, or services to enrolled members.
  • D. loyaltyIntegration
    Indicates the degree to which a loyalty or rewards program is connected, synchronized, or functionally embedded with another system, platform, or service.
  • E. loyaltyProgramName
    Indicates that an entity is associated with or identified by the name of a specific loyalty or rewards program.
  • F. None of above.

Provenance (4 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_69ad8584485081909ed529e890cadc4a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada5e97548819084643586fff2e3cb completed March 8, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b235bf4a008190ba6264103a9d67b7 completed March 12, 2026, 3:40 a.m.
PD Predicate disambiguation batch_69ad9dfbf0348190952a6bca8fc5fed1 completed March 8, 2026, 4:04 p.m.
Created at: March 8, 2026, 3:05 p.m.