Triple

T20701588
Position Surface form Disambiguated ID Type / Status
Subject The Intervention E508795 entity
Predicate hasCastMember P2308 FINISHED
Object Martha Stewart 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: Martha Stewart | Statement: [The Intervention, hasCastMember, Martha Stewart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Stewart
Context triple: [The Intervention, hasCastMember, Martha Stewart]
  • A. Martha Stewart chosen
    Martha Stewart is an American businesswoman, television personality, and lifestyle guru known for her influential media empire focused on cooking, home décor, and entertaining.
  • B. Nancy Teagarten
    Nancy Teagarten is a central character in the comedy film "Drunk Parents," around whom much of the movie’s family and financial chaos revolves.
  • C. Virginia Stewart
    Virginia Stewart was the wife of U.S. Army Major General James Lawton Collins.
  • D. Elizabeth Gibbs
    Elizabeth Gibbs was an American colonial-era woman best known as the mother of Ralph Izard, a prominent South Carolina planter and statesman of the Revolutionary period.
  • E. Elizabeth Gibbs
    Elizabeth Gibbs was the wife of Salem magistrate Jonathan Corwin, who is historically associated with the Salem witch trials of 1692.
  • 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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c18bfac08190bf80beeb3ce1951a completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:12 p.m.