Triple

T560134
Position Surface form Disambiguated ID Type / Status
Subject Cornelis de Witt E13430 entity
Predicate spouse P13 FINISHED
Object Maria van Berckel E58769 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: Maria van Berckel | Statement: [Cornelis de Witt, spouse, Maria van Berckel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria van Berckel
Context triple: [Cornelis de Witt, spouse, Maria van Berckel]
  • A. Suzanna van Baerle
    Suzanna van Baerle was a 17th-century Dutch woman best known as the wife and intellectual companion of poet, composer, and diplomat Constantijn Huygens.
  • B. Maria van Reigersberch
    Maria van Reigersberch was the resourceful wife of jurist Hugo Grotius, best known for orchestrating his famous escape from Loevestein Castle in a book chest.
  • C. Anna van den Corput chosen
    Anna van den Corput was a 17th-century Dutch woman best known as the mother of prominent Grand Pensionary and statesman Johan de Witt.
  • D. Marianne Schuurmans-Wijdeven
    Marianne Schuurmans-Wijdeven is a Dutch politician who serves as the mayor of the municipality of Haarlemmermeer in the Netherlands.
  • E. Anna van Egmond
    Anna van Egmond was a 16th-century Dutch noblewoman and heiress who became the first wife of William the Silent, Prince of Orange.
  • 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_69a4933edcf08190b35ecfd6014caee6 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a499e13694819087a236bffa6601a9 completed March 1, 2026, 7:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69a51035ebc48190b51f2148cb51a20f completed March 2, 2026, 4:21 a.m.
Created at: March 1, 2026, 7:32 p.m.