Triple

T8833397
Position Surface form Disambiguated ID Type / Status
Subject Burgas Bay E210200 entity
Predicate hasNearbyAirport P4363 FINISHED
Object Burgas Airport E210199 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: Burgas Airport | Statement: [Burgas Bay, hasNearbyAirport, Burgas Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burgas Airport
Context triple: [Burgas Bay, hasNearbyAirport, Burgas Airport]
  • A. Burgas Airport chosen
    Burgas Airport is an international airport on Bulgaria’s Black Sea coast that serves the city of Burgas and nearby seaside resorts.
  • B. Plovdiv Airport
    Plovdiv Airport is an international airport in southern Bulgaria serving the city of Plovdiv and the surrounding region, including access to nearby ski resorts.
  • C. Varna Airport
    Varna Airport is an international airport serving the city of Varna and the surrounding Black Sea resort region in Bulgaria.
  • D. Sofia Airport
    Sofia Airport is the main international airport serving Bulgaria’s capital city, Sofia, and one of the country’s busiest air transport hubs.
  • E. Platov International Airport
    Platov International Airport is a major modern airport serving the city of Rostov-on-Don and the surrounding region in southern Russia.
  • 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_69ca8388549c819095fd94eadefbb007 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60670fa48190b2a873f6498de7f6 completed April 1, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfab71962c8190823a1ca1d4fa56f3 completed April 3, 2026, 11:58 a.m.
Created at: March 30, 2026, 6:47 p.m.