Triple

T5021039
Position Surface form Disambiguated ID Type / Status
Subject William Frederick of Nassau-Dietz E112848 entity
Predicate deathPlace P21 FINISHED
Object Leeuwarden E141776 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: Leeuwarden | Statement: [William Frederick of Nassau-Dietz, deathPlace, Leeuwarden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leeuwarden
Context triple: [William Frederick of Nassau-Dietz, deathPlace, Leeuwarden]
  • A. Leeuwarden chosen
    Leeuwarden is a historic city in the northern Netherlands, known as the capital of the province of Friesland and for its rich cultural and architectural heritage.
  • B. Zwolle
    Zwolle is a historic Dutch city in the eastern Netherlands known for its medieval center, cultural heritage, and regional economic importance.
  • C. Venlo
    Venlo is a historic city in the southeastern Netherlands, located near the German border on the river Meuse and known as a regional economic and logistics hub.
  • D. Groningen
    Groningen is a historic province in the northern Netherlands, known for its university city of the same name, flat landscapes, and rich maritime and agricultural heritage.
  • E. Apeldoorn
    Apeldoorn is a city in the province of Gelderland in the Netherlands, known for the royal palace Het Loo and its historical ties to the Dutch monarchy.
  • 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_69bd4435c2f48190be593158cbfcf8a3 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd736399ac8190aa38efc4b4edc6a2 completed March 20, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69de21a949508190ad16b061ead5ed24 completed April 14, 2026, 11:14 a.m.
Created at: March 20, 2026, 1:36 p.m.