Triple

T15280359
Position Surface form Disambiguated ID Type / Status
Subject Bhuj E365251 entity
Predicate hasAirport P105 FINISHED
Object Bhuj Airport E1139454 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: Bhuj Airport | Statement: [Bhuj, hasAirport, Bhuj Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bhuj Airport
Context triple: [Bhuj, hasAirport, Bhuj Airport]
  • A. Rajkot Airport
    Rajkot Airport is a domestic airport serving the city of Rajkot and surrounding regions in the Indian state of Gujarat.
  • B. Vadodara Airport
    Vadodara Airport is a domestic airport in the city of Vadodara, India, serving as one of the key air transport hubs in the state of Gujarat.
  • C. Bhavnagar airport
    Bhavnagar Airport is a domestic airport in Gujarat, India, serving the city of Bhavnagar and its surrounding region with scheduled commercial flights.
  • D. Kandla Airport chosen
    Kandla Airport is a domestic airport in Gujarat, India, serving the port city of Kandla and the nearby town of Gandhidham.
  • E. Jabalpur Airport
    Jabalpur Airport is a domestic airport in Madhya Pradesh, India, serving the city of Jabalpur and its surrounding region.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00e504d8c8190ad6c565a31d1a9bd completed April 15, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff01e092408190aec1561e78ea0acb completed May 9, 2026, 9:44 a.m.
Created at: April 10, 2026, 3:15 a.m.