Triple

T19197112
Position Surface form Disambiguated ID Type / Status
Subject Ropsha ponds E469999 entity
Predicate nearbyLandmark P350 FINISHED
Object Ropsha settlement 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: Ropsha settlement | Statement: [Ropsha ponds, nearbyLandmark, Ropsha settlement]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ropsha settlement
Context triple: [Ropsha ponds, nearbyLandmark, Ropsha settlement]
  • A. Kalinkin settlement
    Kalinkin settlement was a historical district in Saint Petersburg, Russia, that gave its name to several local landmarks and reflected the city’s early urban development.
  • B. Baksan settlement
    Baksan settlement is a small populated area in Russia’s Kabardino-Balkaria region, situated in the North Caucasus near Mount Elbrus.
  • C. Ropsha chosen
    Ropsha is a historic estate and village near Saint Petersburg, Russia, known as the site of Emperor Peter III’s mysterious death in 1762.
  • D. Dzerzhinovo
    Dzerzhinovo is a village in present-day Belarus best known as the birthplace of Soviet statesman and secret police founder Felix Dzerzhinsky.
  • E. Shushary Municipal Settlement
    Shushary Municipal Settlement is an administrative and residential locality within the federal city of Saint Petersburg, Russia.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a695cc8190b84a220f52c51dfc completed April 20, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:07 p.m.