Triple

T21641014
Position Surface form Disambiguated ID Type / Status
Subject Italian cuisine E534088 entity
Predicate hasDish P17589 FINISHED
Object focaccia 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: focaccia | Statement: [Italian cuisine, hasDish, focaccia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: focaccia
Context triple: [Italian cuisine, hasDish, focaccia]
  • A. focaccia genovese chosen
    Focaccia genovese is a classic Ligurian flatbread known for its airy, tender crumb, generous olive oil, and characteristic dimpled surface.
  • B. Crostini
    Crostini is the Linux container system in ChromeOS that allows users to run Linux applications alongside Chrome apps on Chromebooks.
  • C. Panizza
    Panizza is an Italian-origin surname borne by various notable individuals in fields such as religion, arts, and public life.
  • D. francesinha
    Francesinha is a hearty Portuguese sandwich, typically layered with meats and cheese, covered in a rich beer-based sauce and often served with fries.
  • E. Cornetto
    Cornetto is a popular global ice cream brand best known for its cone-shaped frozen desserts filled with ice cream, chocolate, and nuts.
  • 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_69e0c465ae7481908577b7209fdb2a77 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef53917f3c81909e7f4074beecefd3 completed April 27, 2026, 12:16 p.m.
Created at: April 16, 2026, 6:35 p.m.