Triple

T30442476
Position Surface form Disambiguated ID Type / Status
Subject Tokyo (Narita) – Hong Kong E774486 entity
Predicate languageAtDestination P153622 FINISHED
Object Chinese 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: Chinese | Statement: [Tokyo (Narita) – Hong Kong, languageAtDestination, Chinese]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: languageAtDestination
Context triple: [Tokyo (Narita) – Hong Kong, languageAtDestination, Chinese]
  • A. targetLanguage
    Indicates the language that is the intended recipient or focus of a communication, translation, or linguistic operation.
  • B. languageOfSurroundingCountry
    Indicates that a language is the primary or commonly used language in the country surrounding a given place or region.
  • C. languageAtTerminus chosen
    Indicates the language used or associated with the endpoint or terminus of something (such as a route, connection, or communication).
  • D. subjectLanguageRegion
    Indicates that the subject is associated with or uses a language specific to a particular geographic region.
  • E. languageSpecifies
    Indicates that one entity defines or constrains the syntax, semantics, or usage rules that govern how another language or linguistic system is expressed or interpreted.
  • 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_69f22493ef9c8190ae8c2afcb7f994c8 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69ff17be6ad48190963206f2619b1b28 completed May 9, 2026, 11:17 a.m.
PD Predicate disambiguation batch_69ff1724ba24819092c928fcbcb286ec completed May 9, 2026, 11:14 a.m.
Created at: April 29, 2026, 8:08 p.m.