Triple

T20323966
Position Surface form Disambiguated ID Type / Status
Subject Cornelis Kruseman E492283 entity
Predicate placeOfDeath P21 FINISHED
Object Haarlem 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: Haarlem | Statement: [Cornelis Kruseman, placeOfDeath, Haarlem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haarlem
Context triple: [Cornelis Kruseman, placeOfDeath, Haarlem]
  • A. Haarlem chosen
    Haarlem is a historic Dutch city in the province of North Holland, known for its medieval architecture, cultural heritage, and role as a regional center near Amsterdam.
  • B. Utrecht
    Utrecht is a small town in South Africa’s KwaZulu-Natal province, known for its scenic surroundings and historical significance dating back to the 19th century.
  • C. Utrecht
    Utrecht is a historic city and province in the central Netherlands, known for its medieval old town, canals, and role as a religious and cultural center.
  • D. Nijmegen
    Nijmegen is a historic Dutch city near the German border that played a crucial strategic role during World War II, particularly in the Allied advance in 1944.
  • E. Rijswijk
    Rijswijk is a town in the western Netherlands, near The Hague, historically notable as the site where the 1697 Treaty of Rijswijk ended the Nine Years' War.
  • 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6778e59508190bfd7a3ce44d56a93 completed April 20, 2026, 6:59 p.m.
Created at: April 16, 2026, 11:21 a.m.