Triple
T26541561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanzhi, Taihoku Prefecture, Japanese Taiwan |
E671401
|
entity |
| Predicate | usedLanguageLocally |
P115774
|
FINISHED |
| Object | Hakka |
—
|
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: Hakka | Statement: [Sanzhi, Taihoku Prefecture, Japanese Taiwan, usedLanguageLocally, Hakka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedLanguageLocally Context triple: [Sanzhi, Taihoku Prefecture, Japanese Taiwan, usedLanguageLocally, Hakka]
-
A.
languageUsedInLocality
chosen
Indicates that a particular language is used or spoken within a specific locality or geographic area.
-
B.
usesLanguageFor
Indicates that an entity employs a particular language as a tool or medium to perform some activity, function, or purpose.
-
C.
languageUse
Indicates the language or languages an entity uses for communication, expression, or interaction.
-
D.
usedForLanguageSpokenIn
Indicates that something (such as a resource, tool, or medium) is used for expressing or communicating a language that is spoken in a particular place or region.
-
E.
usesLocalLanguageVariant
Indicates that an entity employs a region-specific or localized form of a language rather than a standard or global variant.
- 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_69eeb3206e748190b90c85cc81f38c91 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6247480cc8190a887eedaeb94615c |
completed | May 2, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69f623a7539c8190b71797f583da9f63 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:41 a.m.