Triple

T20114494
Position Surface form Disambiguated ID Type / Status
Subject Peggy Loving E490420 entity
Predicate familyName P18 FINISHED
Object Loving 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: Loving | Statement: [Peggy Loving, familyName, Loving]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Loving
Context triple: [Peggy Loving, familyName, Loving]
  • A. Loving
    Loving is a 2016 historical drama film that portrays the real-life interracial couple Richard and Mildred Loving and their landmark U.S. Supreme Court case that invalidated laws prohibiting interracial marriage.
  • B. Loving
    Loving is an American daytime soap opera created by Agnes Nixon that aired on ABC from 1983 to 1995.
  • C. Loving chosen
    Loving is a surname of English origin borne by various individuals, including those with the family name Sidney Loving.
  • D. Loving
    Loving is a small village located in Eddy County in the southeastern region of the U.S. state of New Mexico.
  • E. The Loving Story
    The Loving Story is a 2011 documentary film that chronicles the real-life interracial marriage and legal battle of Richard and Mildred Loving, whose case led to the landmark 1967 U.S. Supreme Court decision striking down laws banning interracial marriage.
  • 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666e31af081908d8e0c867c388a73 completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:29 p.m.