Triple

T9397774
Position Surface form Disambiguated ID Type / Status
Subject Mary Louise Curtis Bok E226389 entity
Predicate familyName P18 FINISHED
Object Curtis E22875 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: Curtis | Statement: [Mary Louise Curtis Bok, familyName, Curtis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Curtis
Context triple: [Mary Louise Curtis Bok, familyName, Curtis]
  • A. Curtis chosen
    Curtis is a common English surname of Norman origin, historically meaning "courteous" or "polite."
  • B. Curt
    Curt Schilling is a former Major League Baseball pitcher best known for his postseason performances and World Series titles with the Arizona Diamondbacks and Boston Red Sox.
  • C. Jake Curtis
    Jake Curtis is a British filmmaker and photographer, known as the son of screenwriter-director Richard Curtis and broadcaster Emma Freud.
  • D. Garrett
    Garrett is a masculine given name of Old French and Germanic origin, commonly used in English-speaking countries.
  • E. Rey Curtis
    Rey Curtis is a principled yet often rigid NYPD detective on the television series "Law & Order," known for his strong moral convictions and partnership with veteran detective Lennie Briscoe.
  • 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_69ca843170f88190800a8ab2b5fc568e completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd51541020819097da2eb60be73760 completed April 1, 2026, 5:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1011aef64819085cbb7e04c2d87b2 completed April 4, 2026, 12:16 p.m.
Created at: March 30, 2026, 7:46 p.m.