Triple

T11689189
Position Surface form Disambiguated ID Type / Status
Subject Tom Harmon E277823 entity
Predicate child P120 FINISHED
Object Kristin Harmon E55442 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: Kristin Harmon | Statement: [Tom Harmon, child, Kristin Harmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kristin Harmon
Context triple: [Tom Harmon, child, Kristin Harmon]
  • A. Kristin Harmon chosen
    Kristin Harmon was an American actress and painter best known as a member of the Nelson entertainment family and for her appearances on the television series "The Adventures of Ozzie and Harriet."
  • B. Kristin Yancey
    Kristin Yancey is a fictional character from the American television sitcom "Kristin."
  • C. Karen McCullah Lutz
    Karen McCullah Lutz is an American screenwriter best known for co-writing popular romantic comedies such as "10 Things I Hate About You," "Legally Blonde," and "The House Bunny."
  • D. Amy Eshleman
    Amy Eshleman is an American former public librarian and education advocate best known as the wife of former Chicago mayor Lori Lightfoot.
  • E. Kristin Rusk Robinson
    Kristin Rusk Robinson is a screenwriter best known for her work on the animated musical television special and film project "Entergalactic."
  • 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_69d6aafe02d881909900d54ad7d4af84 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a478f4c481908b2ba7b70972590d completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef831d27248190894ffdb12c1ddd4d completed April 27, 2026, 3:39 p.m.
Created at: April 8, 2026, 9:40 p.m.