Triple

T19713757
Position Surface form Disambiguated ID Type / Status
Subject Pskov Airport E473420 entity
Predicate partOf P40 FINISHED
Object Pskov air base 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: Pskov air base | Statement: [Pskov Airport, partOf, Pskov air base]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pskov air base
Context triple: [Pskov Airport, partOf, Pskov air base]
  • A. Nikolaevka air base
    Nikolaevka air base is a Russian military airfield used by Russian Naval Aviation forces, located in the Russian Far East.
  • B. Zavitinsk air base
    Zavitinsk air base is a Russian military airfield in Amur Oblast that has historically hosted strategic bomber units.
  • C. Ramenskoye airfield
    Ramenskoye airfield is a major Russian airfield near Zhukovsky, known for flight testing and hosting the MAKS International Aviation and Space Salon.
  • D. Yeysk air base
    Yeysk air base is a Russian military airfield on the Sea of Azov used primarily for naval aviation training and operations.
  • E. Pskov Airport chosen
    Pskov Airport is a regional airport in Pskov, Russia, providing domestic air services and connecting the city to other parts of the country.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6440b47508190a8a33325b00841dc completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.