Triple

T13531166
Position Surface form Disambiguated ID Type / Status
Subject Grote Markt, Nijmegen E323135 entity
Predicate hasNearbyLandmark P2064 FINISHED
Object Stevenskerk E408479 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: Stevenskerk | Statement: [Grote Markt, Nijmegen, hasNearbyLandmark, Stevenskerk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stevenskerk
Context triple: [Grote Markt, Nijmegen, hasNearbyLandmark, Stevenskerk]
  • A. Stevenskerk chosen
    Stevenskerk is a historic medieval church in Nijmegen, the Netherlands, known as the city's main and oldest church.
  • B. Westerkerk
    Westerkerk is a prominent 17th-century Protestant church in central Amsterdam, renowned for its tall tower and association with Dutch Golden Age history.
  • C. Munsterkerk
    Munsterkerk is a prominent Romanesque church in Roermond, Netherlands, known for its distinctive twin towers and historical significance.
  • D. St. Maartenskerk
    St. Maartenskerk is a historic church in the Dutch town of Tiel, notable for its medieval architecture and prominent tower.
  • E. St. Janskerk
    St. Janskerk is a prominent Gothic church in Maastricht, Netherlands, known for its striking red tower and historic role in the city’s religious and architectural heritage.
  • 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_69d80766a21881909f21a1b7421d3b8a completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafbb34548190a6b44faa48125cd4 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75d95ce008190a915fe5865c38ee5 completed May 3, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:44 p.m.