Triple

T15538729
Position Surface form Disambiguated ID Type / Status
Subject Savini restaurant E370417 entity
Predicate name P16 FINISHED
Object Savini E351253 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: Savini | Statement: [Savini restaurant, name, Savini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Savini
Context triple: [Savini restaurant, name, Savini]
  • A. Savini chosen
    Savini is an Italian surname most famously associated with Tom Savini, a renowned special effects and makeup artist in horror cinema.
  • B. Brusata
    Brusata is a locality in the canton of Ticino in southern Switzerland, situated near the town of Mendrisio close to the Italian border.
  • C. Matarazzo
    Matarazzo is the surname of American actor Gaten Matarazzo, best known for his role as Dustin Henderson on the Netflix series "Stranger Things."
  • D. Fermani
    Fermani are the inhabitants or natives of the Italian city of Fermo, located in the Marche region.
  • E. Zola Predosa
    Zola Predosa is a municipality in the Emilia-Romagna region of northern Italy, situated near the city of Bologna and known for its residential areas and local food and wine production.
  • 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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04430b5188190a555a3cd4fb0c61c completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d626e688190bd93481cfd6cb255 completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 4:07 a.m.