Triple

T21392520
Position Surface form Disambiguated ID Type / Status
Subject Zachary Scott E527690 entity
Predicate spouse P13 FINISHED
Object Ruth Ford 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: Ruth Ford | Statement: [Zachary Scott, spouse, Ruth Ford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Ford
Context triple: [Zachary Scott, spouse, Ruth Ford]
  • A. Ruth Ford chosen
    Ruth Ford was an American actress known for her work in mid-20th-century film and theater, often appearing in character roles on both stage and screen.
  • B. Susan Elizabeth Ford
    Susan Elizabeth Ford is the daughter of former U.S. President Gerald Ford and First Lady Betty Ford, known for her work as an author, photojournalist, and breast cancer awareness advocate.
  • C. Mary Elizabeth Baird
    Mary Elizabeth Baird was the mother of Ruth Bryan Owen, the pioneering American congresswoman and diplomat.
  • D. Leah Ashley
    Leah Ashley is a fashion and lifestyle expert best known as a co-host and style contributor on the daytime talk show FABLife.
  • E. Susan Ross
    Susan Ross is a recurring character on the television sitcom "Seinfeld," known as George Costanza’s fiancée whose tragic death from licking toxic wedding invitation envelopes becomes a darkly comic plot point.
  • 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_69e0b51ff3748190935c0a513c62a12b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b1159a888190aabb5c2a9268bd06 completed April 22, 2026, 11:29 a.m.
Created at: April 16, 2026, 5:13 p.m.