Triple

T21204243
Position Surface form Disambiguated ID Type / Status
Subject Toompea Castle E522535 entity
Predicate occupies P2574 FINISHED
Object Toompea Hill 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: Toompea Hill | Statement: [Toompea Castle, occupies, Toompea Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toompea Hill
Context triple: [Toompea Castle, occupies, Toompea Hill]
  • A. Toompea chosen
    Toompea is a historic limestone hill in central Tallinn, Estonia, that serves as the political and symbolic heart of the country, crowned by Toompea Castle and key government buildings.
  • B. Toompea Castle
    Toompea Castle is a historic fortress and governmental complex in Tallinn, Estonia, that serves as the seat of the national parliament.
  • C. Viru Square
    Viru Square is a central public square and major transport and commercial hub in the heart of Tallinn, Estonia.
  • D. Lutakko Square
    Lutakko Square is a central public event and gathering space in the Lutakko district of Jyväskylä, Finland, often used for concerts, festivals, and community activities.
  • E. Majorstuen
    Majorstuen is a central neighborhood and transport hub in Oslo, Norway, known for its busy junction of metro and tram lines, shopping streets, and residential areas.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7343367308190b1b772d3c8e25dcb completed April 21, 2026, 8:24 a.m.
Created at: April 16, 2026, 3:19 p.m.