Triple

T13998624
Position Surface form Disambiguated ID Type / Status
Subject MAA E336764 entity
Predicate servesAsFocusCityFor P1655 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: [MAA, servesAsFocusCityFor, Air India]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Air India
Context triple: [MAA, servesAsFocusCityFor, 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. Air India Express
    Air India Express is an Indian low-cost airline, primarily operating short-haul international and domestic flights, and is a subsidiary of Air India.
  • C. Jat Airways
    Jat Airways was the former national airline of Serbia and Yugoslavia, operating regional and international flights before being rebranded as Air Serbia.
  • D. Orient Airways
    Orient Airways was a pioneering South Asian airline that later evolved into Pakistan International Airlines, the national flag carrier of Pakistan.
  • E. Tata Airlines
    Tata Airlines was the private Indian airline founded by J. R. D. Tata in the 1930s that later evolved into the national carrier Air India.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb81b208190a961e49a02fa4140 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9f1f6c8190af7ddac920661bd5 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.