Triple

T22869752
Position Surface form Disambiguated ID Type / Status
Subject Roos House E567158 entity
Predicate namedAfter P63 FINISHED
Object Roos family 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: Roos family | Statement: [Roos House, namedAfter, Roos family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roos family
Context triple: [Roos House, namedAfter, Roos family]
  • A. Roos family chosen
    The Roos family is a prominent San Francisco family historically significant enough to have the Roos House in the city named in their honor.
  • B. Hooft family
    The Hooft family was a prominent Dutch regent dynasty from Amsterdam, known for its influential role in the city’s political and cultural life during the Dutch Golden Age.
  • C. Brenninkmeijer family
    The Brenninkmeijer family is a wealthy and influential Dutch-German Catholic business dynasty best known for founding and controlling the international clothing retail chain C&A.
  • D. Alberdingk Thijm family
    The Alberdingk Thijm family is a notable Dutch family known for its cultural and literary contributions in the Netherlands.
  • E. Van der Does family
    The Van der Does family is a Dutch noble lineage historically associated with prominent statesmen, military leaders, and scholars in the Netherlands.
  • 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_69e24589d8348190b96422d13a678bc1 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17f0384a88190a0fbf57b5dca8d5a completed April 29, 2026, 3:46 a.m.
Created at: April 17, 2026, 3:38 p.m.