Triple

T90404
Position Surface form Disambiguated ID Type / Status
Subject Roosevelt family E1816 entity
Predicate earliestKnownAncestor P3891 FINISHED
Object Claes Maartenszen van Rosenvelt
Claes Maartenszen van Rosenvelt was a 17th-century Dutch immigrant to New Netherland who became the progenitor of the American Roosevelt family.
E20456 NE FINISHED

How this triple was built (5 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: Claes Maartenszen van Rosenvelt | Statement: [Roosevelt family, earliestKnownAncestor, Claes Maartenszen van Rosenvelt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Claes Maartenszen van Rosenvelt
Context triple: [Roosevelt family, earliestKnownAncestor, Claes Maartenszen van Rosenvelt]
  • A. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • B. Prince Bernhard of the Netherlands
    Prince Bernhard of the Netherlands was a German-born Dutch prince consort, husband of Queen Juliana, noted for his role in the Dutch resistance during World War II and for founding the World Wildlife Fund.
  • C. Johan Maurits van Nassau-Siegen
    Johan Maurits van Nassau-Siegen was a 17th-century German-Dutch nobleman and military commander best known for his enlightened but expansionist rule over Dutch Brazil and his patronage of science and the arts.
  • D. Rudolf Lange
    Rudolf Lange was a high-ranking SS officer and Holocaust perpetrator who played a key role in mass shootings in Latvia and participated in the Wannsee Conference that coordinated the "Final Solution."
  • E. Simon van Slingelandt
    Simon van Slingelandt was an 18th-century Dutch statesman who served as Grand Pensionary of Holland and played a key role in the political affairs of the Dutch Republic.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Claes Maartenszen van Rosenvelt
Triple: [Roosevelt family, earliestKnownAncestor, Claes Maartenszen van Rosenvelt]
Generated description
Claes Maartenszen van Rosenvelt was a 17th-century Dutch immigrant to New Netherland who became the progenitor of the American Roosevelt family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Claes Maartenszen van Rosenvelt
Target entity description: Claes Maartenszen van Rosenvelt was a 17th-century Dutch immigrant to New Netherland who became the progenitor of the American Roosevelt family.
  • A. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • B. Prince Bernhard of the Netherlands
    Prince Bernhard of the Netherlands was a German-born Dutch prince consort, husband of Queen Juliana, noted for his role in the Dutch resistance during World War II and for founding the World Wildlife Fund.
  • C. Johan Maurits van Nassau-Siegen
    Johan Maurits van Nassau-Siegen was a 17th-century German-Dutch nobleman and military commander best known for his enlightened but expansionist rule over Dutch Brazil and his patronage of science and the arts.
  • D. Rudolf Lange
    Rudolf Lange was a high-ranking SS officer and Holocaust perpetrator who played a key role in mass shootings in Latvia and participated in the Wannsee Conference that coordinated the "Final Solution."
  • E. Simon van Slingelandt
    Simon van Slingelandt was an 18th-century Dutch statesman who served as Grand Pensionary of Holland and played a key role in the political affairs of the Dutch Republic.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: earliestKnownAncestor
Context triple: [Roosevelt family, earliestKnownAncestor, Claes Maartenszen van Rosenvelt]
  • A. geologicalAge
    Indicates the time period in Earth's geological history during which an entity (such as a rock, fossil, or formation) originated or was formed.
  • B. pioneerOf
    Indicates that an entity was among the first to develop, introduce, or significantly advance another entity, concept, or practice.
  • C. eraName
    Indicates the named historical or chronological era associated with an entity or time period.
  • D. ancestralSeatOf
    Indicates that one entity is the traditional or original home, origin place, or foundational location associated with the lineage, heritage, or authority of another entity.
  • E. discoveredBy
    Indicates that something was found, identified, or brought to light through the efforts or actions of a particular agent.
  • F. None of above. chosen

Provenance (7 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_69a24d1a97dc819094e6c021fe9b05a7 completed Feb. 28, 2026, 2:04 a.m.
NER Named-entity recognition batch_69a24feef1b08190bb9525f71cce053e completed Feb. 28, 2026, 2:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2db50ac3881908088683967e9ae9f completed Feb. 28, 2026, 12:10 p.m.
NEDg Description generation batch_69a2dbd90d688190b5ed67850db33782 completed Feb. 28, 2026, 12:13 p.m.
NED2 Entity disambiguation (via description) batch_69a2dc3ed95881909c866ee8ebca122f completed Feb. 28, 2026, 12:14 p.m.
PD Predicate disambiguation batch_69a24eb82d408190b0f9c786152e8e4c completed Feb. 28, 2026, 2:11 a.m.
PDg Predicate description generation batch_69a24fed6b8c819080a6c0cd3b16e6bd completed Feb. 28, 2026, 2:16 a.m.
Created at: Feb. 28, 2026, 2:07 a.m.