Triple

T35734531
Position Surface form Disambiguated ID Type / Status
Subject Four Beauties of ancient China E1032850 entity
Predicate hasIdiom P183867 FINISHED
Object 沉魚落雁 (fish sink, geese fall) 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: 沉魚落雁 (fish sink, geese fall) | Statement: [Four Beauties of ancient China, hasIdiom, 沉魚落雁 (fish sink, geese fall)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasIdiom
Context triple: [Four Beauties of ancient China, hasIdiom, 沉魚落雁 (fish sink, geese fall)]
  • A. hasSlang
    Indicates that one entity is an informal, colloquial, or slang term referring to the other entity.
  • B. pairedWithIdiomatically
    Indicates that one entity is commonly or conventionally paired with another in idiomatic usage or expression.
  • C. hasLatinPhraseMeaning
    Indicates that one entity is a Latin phrase that expresses the meaning or translation of another entity.
  • D. hasMeaningInJapanese
    Indicates that something (such as a word, phrase, or symbol) possesses a specific meaning when interpreted in the Japanese language.
  • E. hasCulturalEquivalent
    Indicates that one entity has a counterpart in another cultural context that plays a similar role, function, or meaning.
  • F. None of above. chosen

Provenance (4 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_69f76e10e59081908d81ad9ce22f40b6 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f7a34f8ee08190a040304635539a8f completed May 3, 2026, 7:34 p.m.
PD Predicate disambiguation batch_69f7a06f125c8190843af194f042a465 completed May 3, 2026, 7:22 p.m.
PDg Predicate description generation batch_69f7a34e80dc8190980d5b7b0b91341d completed May 3, 2026, 7:34 p.m.
Created at: May 3, 2026, 4:05 p.m.