Triple

T6711794
Position Surface form Disambiguated ID Type / Status
Subject Joan Fontaine E153160 entity
Predicate spouse P13 FINISHED
Object Collier Young E510840 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: Collier Young | Statement: [Joan Fontaine, spouse, Collier Young]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Collier Young
Context triple: [Joan Fontaine, spouse, Collier Young]
  • A. Collier Young chosen
    Collier Young was an American screenwriter and film and television producer best known for co-creating the legal drama series "Ironside."
  • B. Cole Young
    Cole Young is a fictional mixed martial artist and the original protagonist introduced in the 2021 film adaptation of Mortal Kombat.
  • C. Toriano Adaryll Jackson
    Toriano Adaryll Jackson, better known as Tito Jackson, is an American musician and original member of the legendary Motown family group The Jackson 5.
  • D. Harry Chandlee
    Harry Chandlee was an American screenwriter and film editor best known for co-writing the Academy Award–winning World War I biographical film "Sergeant York."
  • E. Cress Williams
    Cress Williams is an American actor best known for his television roles, including the lead in the superhero series "Black Lightning" and prominent parts in shows like "Hart of Dixie" and "Prison Break."
  • 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_69c68808d8d8819087369015270788fe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d108acc08190b38b43161d8912b9 completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c700924fdc8190990187fbc1b3ab20 completed March 27, 2026, 10:11 p.m.
Created at: March 27, 2026, 2:06 p.m.