Triple

T20486662
Position Surface form Disambiguated ID Type / Status
Subject Pirita Convent ruins E502612 entity
Predicate locatedIn P40 FINISHED
Object Pirita, Tallinn 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: Pirita, Tallinn | Statement: [Pirita Convent ruins, locatedIn, Pirita, Tallinn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pirita, Tallinn
Context triple: [Pirita Convent ruins, locatedIn, Pirita, Tallinn]
  • A. Pirita chosen
    Pirita is a coastal district of Tallinn, Estonia, known for its beaches, marina, and extensive green areas.
  • B. Tallinn
    Tallinn is the capital and largest city of Estonia, a historic Baltic Sea port known for its well-preserved medieval Old Town and strategic maritime location.
  • C. Haapsalu
    Haapsalu is a small seaside town in western Estonia known for its historic wooden architecture, medieval castle, and traditional seaside resort and spa culture.
  • D. Pāvilosta
    Pāvilosta is a small coastal town in western Latvia known for its Baltic Sea beaches, fishing heritage, and laid-back seaside atmosphere.
  • E. Narva
    Narva is a historic city in northeastern Estonia on the border with Russia, known for its strategic military importance and well-preserved fortress overlooking the Narva River.
  • 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_69e0b4af32848190aea80682b44d5d6e completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69b5b96c0819080c47064143cdbc9 completed April 20, 2026, 9:32 p.m.
Created at: April 16, 2026, 11:34 a.m.