Triple

T8819416
Position Surface form Disambiguated ID Type / Status
Subject Roing E209862 entity
Predicate hasNearbyAirport P4363 FINISHED
Object Dibrugarh Airport E33991 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: Dibrugarh Airport | Statement: [Roing, hasNearbyAirport, Dibrugarh Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dibrugarh Airport
Context triple: [Roing, hasNearbyAirport, Dibrugarh Airport]
  • A. Dibrugarh Airport chosen
    Dibrugarh Airport is a domestic airport in the Indian state of Assam that serves the city of Dibrugarh and the surrounding Upper Assam region.
  • B. Jorhat Airport
    Jorhat Airport is a domestic airport in Assam, India, serving the city of Jorhat and surrounding regions with regional air connectivity.
  • C. Tezpur Airport
    Tezpur Airport is a domestic airport in Tezpur, Assam, India, serving as a regional air transport hub for the surrounding area.
  • D. Dimapur Airport
    Dimapur Airport is a domestic airport in Nagaland, India, serving as the primary air gateway to the state capital, Kohima, and surrounding regions.
  • E. Bagdogra Airport
    Bagdogra Airport is a major international airport in northern West Bengal, India, serving as a key gateway to the Darjeeling, Sikkim, and eastern Himalayan regions.
  • 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_69ca8364e13081909c85fe80f44fe86f completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc600e6e2881908934cbff0ab5d6fd completed April 1, 2026, midnight
NED1 Entity disambiguation (via context triple) batch_69cf6fc96a8481909d09835845ccdcbf completed April 3, 2026, 7:44 a.m.
Created at: March 30, 2026, 6:46 p.m.