Triple

T9240425
Position Surface form Disambiguated ID Type / Status
Subject Sokol E222042 entity
Predicate hasAdjacentStation P231 FINISHED
Object Aeroport E222043 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: Aeroport | Statement: [Sokol, hasAdjacentStation, Aeroport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aeroport
Context triple: [Sokol, hasAdjacentStation, Aeroport]
  • A. Aeroport chosen
    Aeroport is a Moscow Metro station on the Zamoskvoretskaya Line, named after the nearby Khodynka Aerodrome area.
  • B. Flughafen
    Flughafen is the Nuremberg U-Bahn station that serves Nuremberg Airport, providing direct metro access between the airport and the city.
  • C. Vinci Airports
    Vinci Airports is a global airport operator that manages and develops a large network of airports across multiple countries as part of the Vinci Group’s transport infrastructure portfolio.
  • D. Gillot Airport
    Gillot Airport is the former name of Roland Garros Airport, the main international airport serving Réunion Island in the Indian Ocean.
  • E. HEF Airport
    HEF Airport is the regional public airport serving Manassas, Virginia, handling general aviation and some corporate and charter traffic for the Washington, D.C. metropolitan area.
  • 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_69ca83ee26cc81909ac624e190597d6d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccf0a3888c8190b72d8d0b850bdfbc completed April 1, 2026, 10:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077db03048190b9c1f0812da21733 completed April 4, 2026, 2:30 a.m.
Created at: March 30, 2026, 7:30 p.m.