Triple

T2936701
Position Surface form Disambiguated ID Type / Status
Subject South Beveland E79285 entity
Predicate hasTown P847 FINISHED
Object Kapelle E72496 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: Kapelle | Statement: [South Beveland, hasTown, Kapelle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kapelle
Context triple: [South Beveland, hasTown, Kapelle]
  • A. Kapelle chosen
    Kapelle is a small municipality and town in the Dutch province of Zeeland, known for its agricultural landscape and historic village character.
  • B. Felsenkirche
    Felsenkirche is a historic hilltop Lutheran church in Lüderitz, Namibia, known for its striking Gothic Revival architecture and panoramic views over the coastal town.
  • C. Bata Cathedral
    Bata Cathedral is a prominent Roman Catholic church and architectural landmark located in the coastal city of Bata in Equatorial Guinea.
  • D. Corona Chapel
    Corona Chapel is a historic chapel within Canterbury Cathedral, traditionally associated with the veneration of Saint Thomas Becket and notable for its medieval architecture and stained glass.
  • E. Pagodenburg
    Pagodenburg is a small, ornate garden pavilion in the park of Nymphenburg Palace in Munich, notable for its chinoiserie-inspired architecture and decorative interiors.
  • 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_69ad8b0fbab081908f6a61567c045d8d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad983df5e08190939cd8acf8ad5b55 completed March 8, 2026, 3:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0867edf3481909c5fa9d02c5f11b3 completed March 10, 2026, 9 p.m.
Created at: March 8, 2026, 2:56 p.m.