Triple

T18064978
Position Surface form Disambiguated ID Type / Status
Subject Martini & Rossi E432272 entity
Predicate brand P1500 FINISHED
Object Martini 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: Martini | Statement: [Martini & Rossi, brand, Martini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martini
Context triple: [Martini & Rossi, brand, Martini]
  • A. Martini
    Martini is a common Italian surname shared by various notable individuals in fields such as acting, sports, and politics.
  • B. Martini chosen
    Martini is an iconic Italian brand best known for its vermouth and sponsorship of high-profile motorsport teams.
  • C. French Martini
    The French Martini is a modern vodka-based cocktail known for its fruity blend of pineapple juice and raspberry liqueur, yielding a smooth, slightly sweet, and elegant drink.
  • D. Brandy Manhattan
    Brandy Manhattan is a cocktail that substitutes brandy for the traditional whiskey in a Manhattan, typically mixed with sweet vermouth and bitters and served straight up or on the rocks.
  • E. Sazerac
    Sazerac is a classic New Orleans cocktail typically made with rye whiskey (or cognac), sugar, Peychaud’s bitters, and an absinthe-rinsed glass.
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4cce81de88190bd94d4ccee3e180c completed April 19, 2026, 12:39 p.m.
Created at: April 10, 2026, 10:26 a.m.