Triple

T6885302
Position Surface form Disambiguated ID Type / Status
Subject Kardenakhi E158902 entity
Predicate wineProductionMethod P14224 FINISHED
Object qvevri fermentation 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: qvevri fermentation | Statement: [Kardenakhi, wineProductionMethod, qvevri fermentation]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: wineProductionMethod
Context triple: [Kardenakhi, wineProductionMethod, qvevri fermentation]
  • A. traditionalVinification
    Indicates that a wine is produced using traditional or historically established winemaking methods rather than modern or industrial techniques.
  • B. producesWine
    Indicates that one entity creates or manufactures wine as a product.
  • C. sparklingWineMethod
    Indicates that a wine is produced using a specific method or process for making sparkling wine.
  • D. vinification chosen
    Indicates the process by which grapes (or other fruits) are transformed into wine through fermentation and related winemaking steps.
  • E. hasWineMakingTradition
    Indicates that a place or group has an established, culturally recognized history and practice of producing wine.
  • 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_69c688342f6c8190ad7eea6ba262db99 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d90bc32c8190baf5bf785146f3e8 completed March 27, 2026, 7:22 p.m.
PD Predicate disambiguation batch_69c6d7b53e9881909ec298daa9f1913b completed March 27, 2026, 7:17 p.m.
Created at: March 27, 2026, 2:23 p.m.