Triple

T9726580
Position Surface form Disambiguated ID Type / Status
Subject Robert Montgomery E235627 entity
Predicate child P120 FINISHED
Object Elizabeth Montgomery E214696 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: Elizabeth Montgomery | Statement: [Robert Montgomery, child, Elizabeth Montgomery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Montgomery
Context triple: [Robert Montgomery, child, Elizabeth Montgomery]
  • A. Elizabeth Montgomery chosen
    Elizabeth Montgomery was an American actress best known for her starring role as the witch Samantha Stephens on the classic television sitcom "Bewitched."
  • B. Linda Gray
    Linda Gray is an American actress best known for her role as Sue Ellen Ewing on the long-running television series "Dallas."
  • C. Linda Gray
    Linda Gray is the longtime wife of Bee Gees singer Barry Gibb, known for her enduring marriage to the music icon since the 1970s.
  • D. Linda Gray Sexton
    Linda Gray Sexton is an American writer and memoirist known for her novels and for editing and chronicling the life and work of her mother, poet Anne Sexton.
  • E. Carolyn Jones
    Carolyn Jones is a former American professional women's basketball player best known for her standout career in the ABL and WNBA during the 1990s.
  • 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_69ca84d0fad481909cdd45aa77416c48 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e798c348190885b79d7dffc9d8d completed April 1, 2026, 10:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c40575f48190807b6a3f10e63b41 completed April 5, 2026, 2:08 a.m.
Created at: March 30, 2026, 8:21 p.m.