Triple

T18828534
Position Surface form Disambiguated ID Type / Status
Subject Rebecca Romijn E460459 entity
Predicate familyName P18 FINISHED
Object Romijn 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: Romijn | Statement: [Rebecca Romijn, familyName, Romijn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romijn
Context triple: [Rebecca Romijn, familyName, Romijn]
  • A. Romijn chosen
    Romijn is a Dutch surname most notably associated with American actress and former model Rebecca Romijn.
  • B. Jeroen
    Jeroen is a common Dutch male given name, often associated internationally with figures such as politician Jeroen Dijsselbloem.
  • C. Reuver
    Reuver is a village in the Dutch province of Limburg, situated along the River Meuse and served by the Maaslijn railway.
  • D. Dirk De Jonge
    Dirk De Jonge was an American communist and political activist best known for his role in the landmark U.S. Supreme Court case De Jonge v. Oregon, which expanded protections for freedom of assembly.
  • E. Victor Heerman
    Victor Heerman was a British-born American screenwriter and film director best known for co-writing the Academy Award–winning adaptation of "Little Women" (1933).
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a99554848190933dd2810f5c810f completed April 20, 2026, 4:20 a.m.
Created at: April 10, 2026, 11:56 a.m.