Triple

T13804333
Position Surface form Disambiguated ID Type / Status
Subject Kheria Airport E331721 entity
Predicate hasICAOCode P419 FINISHED
Object VIAG E329572 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: VIAG | Statement: [Kheria Airport, hasICAOCode, VIAG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: VIAG
Context triple: [Kheria Airport, hasICAOCode, VIAG]
  • A. VIAG
    VIAG was a major German industrial and energy conglomerate that later merged into E.ON.
  • B. VIAG chosen
    VIAG is the ICAO airport code for Agra Airport, a public and military airfield serving the city of Agra in Uttar Pradesh, India.
  • C. VIAM
    VIAM is the ICAO airport code for Ambala Air Force Station, a major Indian Air Force base located in Ambala, Haryana, India.
  • D. VIAB
    VIAB was the NASDAQ stock ticker symbol for Viacom Inc., a major American media conglomerate known for owning networks such as MTV, Nickelodeon, and Comedy Central.
  • E. VIAR
    VIAR is the ICAO airport code for Sri Guru Ram Dass Jee International Airport serving Amritsar, 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_69d81c59f8808190a851bc56afdc55e9 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de026c36108190a7436034a730a261 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b08db39c8190a76637b36b77d643 completed May 3, 2026, 8:31 p.m.
Created at: April 9, 2026, 10:12 p.m.