Triple

T3341500
Position Surface form Disambiguated ID Type / Status
Subject Rajiv Gandhi International Airport E70269 entity
Predicate focusCityFor P164 FINISHED
Object Air India E100865 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: Air India | Statement: [Rajiv Gandhi International Airport, focusCityFor, Air India]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Air India
Context triple: [Rajiv Gandhi International Airport, focusCityFor, Air India]
  • A. Air India chosen
    Air India is the flag carrier airline of India, operating domestic and international flights across numerous destinations worldwide.
  • B. SpiceJet
    SpiceJet is a major Indian low-cost airline operating extensive domestic and regional international services.
  • C. Alliance Air
    Alliance Air is an Indian regional airline that operates domestic flights connecting smaller cities and towns, often serving as a feeder carrier to larger national airlines.
  • D. Vistara
    Vistara is an Indian full-service airline known for its premium in-flight experience and joint venture ownership by Tata Group and Singapore Airlines.
  • E. AirAsia India
    AirAsia India is a low-cost airline based in India that operates domestic flights across the country as part of the AirAsia group.
  • 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_69ad85a405e48190b6e68de7cf9f319e completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb1c0ae44819091c851569eaf4565 completed March 8, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a946ba88190bd40ba7481baf28d completed March 12, 2026, 7:57 p.m.
Created at: March 8, 2026, 3:12 p.m.