Triple

T12247707
Position Surface form Disambiguated ID Type / Status
Subject Anthony Dominick Benedetto E291890 entity
Predicate spouse P13 FINISHED
Object Susan Crow E291900 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: Susan Crow | Statement: [Anthony Dominick Benedetto, spouse, Susan Crow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Crow
Context triple: [Anthony Dominick Benedetto, spouse, Susan Crow]
  • A. Susan Crow chosen
    Susan Crow is an American former teacher and philanthropist best known as the third wife and longtime partner of legendary singer Tony Bennett.
  • B. Jennifer Warnes
    Jennifer Warnes is an American singer-songwriter and interpreter of Leonard Cohen’s work, known for her rich vocals and hit duets such as “(I’ve Had) The Time of My Life.”
  • C. Joan Osborne
    Joan Osborne is an American singer-songwriter best known for her soulful vocals and the 1995 hit single "One of Us."
  • D. Suzanne Vega
    Suzanne Vega is an American singer-songwriter known for her literate, folk-inspired songs such as "Luka" and "Tom's Diner," which gained prominence in the 1980s and 1990s.
  • E. Shelly Wright
    Shelly Wright is known as the former spouse of television host and producer Jeff Probst, famed for hosting the reality series "Survivor."
  • 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_69d6ab67950c8190be08450a06228c4b completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cc50d808190a3c8d1ada31a6a91 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e620ed88190b46d256ebe994714 completed May 2, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:51 p.m.