Triple

T20137830
Position Surface form Disambiguated ID Type / Status
Subject EETN E491070 entity
Predicate airportName P4100 FINISHED
Object Lennart Meri Tallinn Airport 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: Lennart Meri Tallinn Airport | Statement: [EETN, airportName, Lennart Meri Tallinn Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lennart Meri Tallinn Airport
Context triple: [EETN, airportName, Lennart Meri Tallinn Airport]
  • A. Lennart Meri Tallinn Airport chosen
    Lennart Meri Tallinn Airport is the main international airport serving Estonia’s capital, Tallinn, and the country’s largest air travel hub.
  • B. Tartu Airport
    Tartu Airport is a regional airport in Estonia serving the city of Tartu and the surrounding area with domestic and limited international flights.
  • C. Kuressaare Airport
    Kuressaare Airport is a regional airport on Saaremaa Island in Estonia that provides domestic and limited international air connections for the town of Kuressaare and its surroundings.
  • D. Pärnu Airport
    Pärnu Airport is a regional airport in southwestern Estonia that serves the city of Pärnu with domestic and limited international flights.
  • E. Viedma Airport
    Viedma Airport is a regional public airport serving the city of Viedma and surrounding areas in Argentina’s Río Negro Province.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6676879f48190a59da04393d2a8cc completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:32 p.m.