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.