Triple

T12421087
Position Surface form Disambiguated ID Type / Status
Subject William Russell E296772 entity
Predicate workedWith P398 FINISHED
Object Carole Ann Ford E417906 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: Carole Ann Ford | Statement: [William Russell, workedWith, Carole Ann Ford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carole Ann Ford
Context triple: [William Russell, workedWith, Carole Ann Ford]
  • A. Carole Ann Ford chosen
    Carole Ann Ford is a British actress best known for originating the role of Susan Foreman, the Doctor’s granddaughter, in the early years of the long-running science fiction series Doctor Who.
  • B. Cheryl Ford
    Cheryl Ford is a former WNBA forward best known for helping lead the Detroit Shock to multiple championships and for being the daughter of NBA legend Karl Malone.
  • C. Carole Ann Ferguson
    Carole Ann Ferguson is the mother of Australian actor Ben Mendelsohn.
  • D. Carole Werner
    Carole Werner is a character appearing in the 1965 romantic comedy film "What’s New Pussycat?".
  • E. Marilyn Rowe
    Marilyn Rowe is a distinguished Australian ballerina and former principal dancer renowned for her long and influential career with The Australian Ballet.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d702b1481909db5f5bed6292ce0 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65ea44a808190af2c5a6633120814 completed May 2, 2026, 8:29 p.m.
Created at: April 8, 2026, 9:55 p.m.