Triple

T3903294
Position Surface form Disambiguated ID Type / Status
Subject Delta Sky Club E90545 entity
Predicate relatedTo P37 FINISHED
Object SkyMiles E36412 NE FINISHED

How this triple was built (2 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: SkyMiles | Statement: [Delta Sky Club, relatedTo, SkyMiles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SkyMiles
Context triple: [Delta Sky Club, relatedTo, SkyMiles]
  • A. SkyMiles chosen
    SkyMiles is Delta Air Lines’ frequent flyer loyalty program that lets members earn and redeem miles for flights, upgrades, and other travel rewards.
  • B. PhoenixMiles
    PhoenixMiles is the loyalty and rewards program that allows Shenzhen Airlines passengers to earn and redeem miles for flights and related travel benefits.
  • C. Avios
    Avios is a travel rewards currency used by several major airlines and loyalty programs, allowing members to earn and redeem points for flights and related travel benefits.
  • D. Air Miles (in the UK market)
    Air Miles was a popular UK travel rewards loyalty scheme that allowed members to collect points from everyday spending and redeem them for flights and other travel-related benefits.
  • E. AAdvantage
    AAdvantage is American Airlines’ frequent-flyer loyalty program, offering members miles, elite status, and travel-related rewards.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed95d315881908cbf1bf4a7215fbf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeecf5a7188190a1c722ec83e3c6cd completed March 9, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51ca7636081908f98c4e22617f808 completed March 14, 2026, 8:30 a.m.
Created at: March 9, 2026, 3:21 p.m.