Triple

T14576900
Position Surface form Disambiguated ID Type / Status
Subject Manhattan (cocktail) E342075 entity
Predicate typicalRatio P57967 FINISHED
Object 2:1 whiskey to sweet vermouth LITERAL 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: 2:1 whiskey to sweet vermouth | Statement: [Manhattan (cocktail), typicalRatio, 2:1 whiskey to sweet vermouth]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typicalRatio
Context triple: [Manhattan (cocktail), typicalRatio, 2:1 whiskey to sweet vermouth]
  • A. radiusRatio
    Indicates the proportional relationship between one radius and another, typically expressing how large one is relative to the other.
  • B. previousRatio
    Indicates the proportional relationship between two quantities as they existed in a prior or earlier state or time period.
  • C. typicalMeasure chosen
    Indicates the standard or characteristic quantitative measure typically associated with something, such as its usual size, weight, duration, or other magnitude.
  • D. النسب
    Indicates a genealogical or familial relationship linking one entity to another through lineage or descent.
  • E. isProportionalTo
    Indicates that one quantity varies in constant ratio to another, so when one changes, the other changes by a fixed multiplicative factor.
  • F. None of above.

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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb3f5ec448190b2ef887fdf7b633e completed April 14, 2026, 9:39 p.m.
PD Predicate disambiguation batch_69de656a953481909a4645b004c40de7 completed April 14, 2026, 4:03 p.m.
Created at: April 10, 2026, 1:24 a.m.