Triple

T22248193
Position Surface form Disambiguated ID Type / Status
Subject Vuku E549900 entity
Predicate hasChurch P15000 FINISHED
Object Vuku Church 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: Vuku Church | Statement: [Vuku, hasChurch, Vuku Church]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vuku Church
Context triple: [Vuku, hasChurch, Vuku Church]
  • A. Vuku Church chosen
    Vuku Church is a historic parish church in the village of Vuku in Trøndelag county, Norway, serving the local Lutheran congregation of the Church of Norway.
  • B. Kaarma Church
    Kaarma Church is a historic medieval stone church located in the village of Kaarma on Saaremaa Island in Estonia.
  • C. Flisa Church
    Flisa Church is a parish church in the village of Flisa in Norway, serving as a local center for Christian worship and community activities.
  • D. Arka Pana Church
    Arka Pana Church is a prominent Roman Catholic church in Kraków’s Nowa Huta district, known for its modernist architecture and symbolic role in Poland’s religious and anti-communist history.
  • E. Laihia Church
    Laihia Church is a historic Lutheran church located in the municipality of Laihia in western Finland.
  • 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_69e11e41d9408190bd770cf282e22753 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f13219dc3481908dd987c4e98623e6 completed April 28, 2026, 10:18 p.m.
Created at: April 16, 2026, 8:38 p.m.