Triple

T15908762
Position Surface form Disambiguated ID Type / Status
Subject Valerie E385790 entity
Predicate portrayedBy P1507 FINISHED
Object Carol Kane E251200 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: Carol Kane | Statement: [Valerie, portrayedBy, Carol Kane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Kane
Context triple: [Valerie, portrayedBy, Carol Kane]
  • A. Carol Kane chosen
    Carol Kane is an American actress known for her distinctive voice and quirky, offbeat roles in film, television, and theater, including acclaimed performances in works like "Hester Street," "Taxi," and "The Princess Bride."
  • B. Deborah Rush
    Deborah Rush is an American actress known for her character roles in film, television, and theater, including appearances in comedies and independent productions.
  • C. Frances Miles
    Frances Miles was the mother of American rock and funk drummer and singer Buddy Miles.
  • D. Linda Purl
    Linda Purl is an American actress and singer best known for her roles on television series such as "Happy Days," "Matlock," and "The Office."
  • E. Debbi Morgan
    Debbi Morgan is an American actress best known for her Emmy-winning role as Angie Hubbard on the soap opera "All My Children" and for her work in film and television spanning several decades.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565d2f048190a40379ceae00411a completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001f7f439c8190b4bcd84e35aa291e completed May 10, 2026, 6:02 a.m.
Created at: April 10, 2026, 4:52 a.m.