Triple

T21327272
Position Surface form Disambiguated ID Type / Status
Subject Kathryn Crosby E525790 entity
Predicate hasChild P369 FINISHED
Object Harry Crosby 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: Harry Crosby | Statement: [Kathryn Crosby, hasChild, Harry Crosby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Crosby
Context triple: [Kathryn Crosby, hasChild, Harry Crosby]
  • A. Harry Crosby chosen
    Harry Crosby is an American investment banker and philanthropist, best known as one of the sons of legendary singer and actor Bing Crosby.
  • B. Harry Crosby
    Harry Crosby is an American actor best known for his role in the classic 1980 slasher film "Friday the 13th."
  • C. Christopher Morley
    Christopher Morley was an American journalist, novelist, essayist, and poet known for his witty, urbane writing and popular works in early 20th-century literature.
  • D. Ernest Howard Crosby
    Ernest Howard Crosby was an American author, social reformer, and advocate of Tolstoyan nonviolence active in the late 19th and early 20th centuries.
  • E. Irving Cummings
    Irving Cummings was an American film director and actor active during the early to mid-20th century, known for directing numerous Hollywood features including musicals and comedies.
  • 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7ab4a796081908148ec9106362d3d completed April 21, 2026, 4:52 p.m.
Created at: April 16, 2026, 4:41 p.m.