Triple

T17928473
Position Surface form Disambiguated ID Type / Status
Subject Donna Winston E448261 entity
Predicate portrayedBy P1507 FINISHED
Object Sprague Grayden 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: Sprague Grayden | Statement: [Donna Winston, portrayedBy, Sprague Grayden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sprague Grayden
Context triple: [Donna Winston, portrayedBy, Sprague Grayden]
  • A. Sprague Grayden chosen
    Sprague Grayden is an American actress known for her roles in television series such as "Jericho," "Six Feet Under," and "24," as well as in horror films.
  • B. Jakob Grayson
    Jakob Grayson is a fictional character from Joe Hill’s post-apocalyptic novel "The Fireman," set in a world ravaged by a deadly spore that causes spontaneous combustion.
  • C. Grady
    Grady is a masculine given name of Irish origin, often used in English-speaking countries.
  • D. Griffin
    The Griffin is the mythical lion-eagle creature that serves as the official mascot of the College of William & Mary, symbolizing the school’s blend of strength, wisdom, and historical heritage.
  • E. Griffin
    Griffin is a surname of English origin borne by numerous notable individuals across fields such as architecture, politics, sports, and entertainment.
  • 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4a5505af88190aa7a5cfee0baa3a4 completed April 19, 2026, 9:50 a.m.
Created at: April 10, 2026, 10:20 a.m.