Triple

T21538429
Position Surface form Disambiguated ID Type / Status
Subject Andong E531413 entity
Predicate knownFor P22 FINISHED
Object Andong soju 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: Andong soju | Statement: [Andong, knownFor, Andong soju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andong soju
Context triple: [Andong, knownFor, Andong soju]
  • A. Soju chosen
    Soju is a clear, typically distilled Korean spirit, often made from rice or other grains, known for its relatively mild taste and central role in Korean drinking culture.
  • B. Shaoxing rice wine
    Shaoxing rice wine is a traditional Chinese fermented rice wine from Shaoxing, Zhejiang, renowned for its rich, mellow flavor and common use in both drinking and cooking.
  • C. Baeggu
    Baeggu is an Oceanic language of the Meso-Melanesian group spoken by a small community in the Solomon Islands.
  • D. Harbin beer
    Harbin beer is a well-known Chinese lager originating from Harbin, recognized as one of China’s oldest and most popular beer brands.
  • E. Baerami
    Baerami is a rural locality in the Upper Hunter region of New South Wales, Australia, known for its agricultural land and proximity to Wollemi National Park.
  • 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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee9d0fdf448190b47ac7c28904f86b completed April 26, 2026, 11:17 p.m.
Created at: April 16, 2026, 6:27 p.m.