Triple

T4042088
Position Surface form Disambiguated ID Type / Status
Subject Palace Bridge E83972 entity
Predicate alsoKnownAs P39 FINISHED
Object Dvortsoviy Most E151562 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: Dvortsoviy Most | Statement: [Palace Bridge, alsoKnownAs, Dvortsoviy Most]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dvortsoviy Most
Context triple: [Palace Bridge, alsoKnownAs, Dvortsoviy Most]
  • A. Černý Most
    Černý Most is a terminal station on Prague Metro’s Line B serving the large housing estate and commercial area of the same name in northeastern Prague.
  • B. Kuznetsky Most
    Kuznetsky Most is a Moscow Metro station on the Tagansko–Krasnopresnenskaya Line, located in the city center near the historic Kuznetsky Most Street.
  • C. Kazansky Bridge chosen
    Kazansky Bridge is a historic bridge in central Saint Petersburg, Russia, spanning the Griboyedov Canal close to Kazan Cathedral and the city’s main thoroughfares.
  • D. Můstek
    Můstek is a major interchange station in the center of Prague where the city’s metro lines A and B intersect beneath Wenceslas Square.
  • E. Володарский мост
    Володарский мост — это автомобильный и трамвайный мост через Неву в Санкт-Петербурге, соединяющий левобережные и правобережные районы города.
  • 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_69aed92f7cf0819098e0539bdcc3767f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb5b65c08190ba3f340ed18737f8 completed March 9, 2026, 4:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5564d0fb881909ba645714be27b95 completed March 14, 2026, 12:36 p.m.
Created at: March 9, 2026, 3:37 p.m.