Triple

T22325404
Position Surface form Disambiguated ID Type / Status
Subject Anichkov Garden E551888 entity
Predicate locatedOn P40 FINISHED
Object Nevsky Prospekt 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: Nevsky Prospekt | Statement: [Anichkov Garden, locatedOn, Nevsky Prospekt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nevsky Prospekt
Context triple: [Anichkov Garden, locatedOn, Nevsky Prospekt]
  • A. Nevsky Prospekt chosen
    Nevsky Prospekt is the main avenue and one of the most famous streets in St. Petersburg, known for its historic architecture, cultural institutions, and role as the city’s central thoroughfare.
  • B. Leninsky Prospekt
    Leninsky Prospekt is a major avenue in Moscow, Russia, known for its wide thoroughfare, Soviet-era architecture, and prominent landmarks.
  • C. Leninsky Prospekt
    Leninsky Prospekt is a major avenue and transport artery in Saint Petersburg, Russia, known for connecting residential districts with the city’s broader road network.
  • D. Krasny Prospekt
    Krasny Prospekt is a metro station in Novosibirsk, Russia, serving one of the city’s main central thoroughfares.
  • E. Nakhimovsky Prospekt
    Nakhimovsky Prospekt is a Moscow Metro station serving the Serpukhovsko–Timiryazevskaya Line in the south of Moscow.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15768696481909be124e86c23d551 completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:42 p.m.