Triple

T18396198
Position Surface form Disambiguated ID Type / Status
Subject Sarah Frye E449876 entity
Predicate name P16 FINISHED
Object Sarah Frye 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: Sarah Frye | Statement: [Sarah Frye, name, Sarah Frye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Frye
Context triple: [Sarah Frye, name, Sarah Frye]
  • A. Sarah Frye chosen
    Sarah Frye is a notable individual distinguished enough to be recognized as a prominent bearer of the Frye surname.
  • B. Carol Ferris
    Carol Ferris is a prominent DC Comics character best known as a Star Sapphire and the longtime romantic partner and occasional adversary of Green Lantern Hal Jordan.
  • C. Lucy McFadden
    Lucy McFadden is the young daughter of the main female protagonist in the romantic comedy film "The Goodbye Girl," whose presence and personality significantly shape the story’s emotional core.
  • D. Christina Fagan
    Christina Fagan is a notable individual recognized as a prominent bearer of the surname Fagan.
  • E. Grace Hawkins
    Grace Hawkins is the seemingly mild-mannered yet secretly murderous housekeeper at the center of the dark comedy film "Keeping Mum."
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e51846bb4c8190990f42a792a78ee0 completed April 19, 2026, 6 p.m.
Created at: April 10, 2026, 10:46 a.m.