Triple

T17658904
Position Surface form Disambiguated ID Type / Status
Subject Travilla E440196 entity
Predicate familyName P18 FINISHED
Object Travilla 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: Travilla | Statement: [Travilla, familyName, Travilla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Travilla
Context triple: [Travilla, familyName, Travilla]
  • A. Travilla chosen
    Travilla was an American costume designer best known for creating some of Marilyn Monroe’s most iconic film dresses, including those in "Gentlemen Prefer Blondes."
  • B. Tibbits
    Tibbits is an English-language surname borne by various notable individuals across different fields.
  • C. Trumbauer
    Trumbauer is a surname most notably associated with American architect Horace Trumbauer, known for his grand Gilded Age mansions and institutional buildings.
  • D. Shanly
    Shanly is a small rural community located within the Township of South Dundas in eastern Ontario, Canada.
  • E. Toshley
    Toshley is a collectible gnome-themed legendary minion card from Hearthstone’s Goblins vs Gnomes expansion, known for generating Spare Parts spells through its battlecry and deathrattle effects.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46ea469448190b2753571f8493aef completed April 19, 2026, 5:56 a.m.
Created at: April 10, 2026, 9:37 a.m.