Triple

T12001755
Position Surface form Disambiguated ID Type / Status
Subject Montgomery Clift E285680 entity
Predicate sibling P363 FINISHED
Object Roberta Clift E285680 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: Roberta Clift | Statement: [Montgomery Clift, sibling, Roberta Clift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roberta Clift
Context triple: [Montgomery Clift, sibling, Roberta Clift]
  • A. Roberta Clift chosen
    Roberta Clift is known as the sister of acclaimed American actor Montgomery Clift.
  • B. Barbara Clough
    Barbara Clough was the long-time wife and partner of legendary English football manager Brian Clough, known for her supportive role throughout his career and family life.
  • C. Helen Morris
    Helen Morris is an American book editor and the longtime wife of acclaimed film director Martin Scorsese.
  • D. Beryl Clark
    Beryl Clark was an American football player best known for playing as a halfback for the University of Oklahoma in the late 1930s.
  • E. Fran Dodsworth
    Fran Dodsworth is a central character in the stage adaptation of Sinclair Lewis's novel "Dodsworth," known as the vain and restless wife whose pursuit of youth and status strains her marriage.
  • 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_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903c36b248190b446b17def94885b completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f48ae4733c81909956cc8d6bae343a completed May 1, 2026, 11:13 a.m.
Created at: April 8, 2026, 9:46 p.m.