Triple

T19264545
Position Surface form Disambiguated ID Type / Status
Subject Tivat Airport E481736 entity
Predicate operator P179 FINISHED
Object Airports of Montenegro NE NERFINISHED

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: Airports of Montenegro | Statement: [Tivat Airport, operator, Airports of Montenegro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Airports of Montenegro
Context triple: [Tivat Airport, operator, Airports of Montenegro]
  • A. Airports of Montenegro chosen
    Airports of Montenegro is the state-owned company responsible for managing and operating Montenegro’s main international airports.
  • B. Airports of Serbia
    Airports of Serbia is a state-owned company responsible for managing and operating several civil airports across Serbia.
  • C. Podgorica Airport
    Podgorica Airport is the main international airport serving Montenegro’s capital city and one of the country’s primary air gateways.
  • D. Pristina International Airport
    Pristina International Airport is the main international airport serving Kosovo, handling the majority of the country's passenger and air cargo traffic.
  • E. Belgrade Airport
    Belgrade Airport is the main international airport serving Serbia’s capital, Belgrade, and one of the busiest air hubs in the Balkans.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb8bce6881908395836960762672 completed April 20, 2026, 10:10 a.m.
Created at: April 10, 2026, 1:29 p.m.