Triple

T22681723
Position Surface form Disambiguated ID Type / Status
Subject Terazije E560498 entity
Predicate knownFor P22 FINISHED
Object Hotel Moskva 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: Hotel Moskva | Statement: [Terazije, knownFor, Hotel Moskva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hotel Moskva
Context triple: [Terazije, knownFor, Hotel Moskva]
  • A. Hotel Moskva chosen
    Hotel Moskva is a historic and iconic luxury hotel in central Belgrade, renowned for its distinctive Art Nouveau architecture and cultural significance.
  • B. Moscow Hotel
    Moscow Hotel was a historic Soviet-era hotel in central Moscow that later underwent redevelopment and reopened as the luxury Four Seasons Hotel Moscow.
  • C. Hotel National Moscow
    Hotel National Moscow is a historic luxury hotel in central Moscow, renowned for its classical architecture and proximity to the Kremlin and Red Square.
  • D. Oktyabrskaya Hotel
    Oktyabrskaya Hotel is a historic and centrally located hotel in Saint Petersburg, Russia, known for serving travelers near the city's major transport and cultural hubs.
  • E. Rossonian Hotel
    The Rossonian Hotel is a historic jazz-era hotel and nightclub in Denver’s Five Points neighborhood, long celebrated as a cultural hub for Black musicians and travelers.
  • 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_69e2454bfd00819099115715a22cb057 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1786113a881908f60285054d7ecfb completed April 29, 2026, 3:17 a.m.
Created at: April 17, 2026, 3:12 p.m.