Triple
T9483679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pe̍h-ōe-jī |
E228708
|
entity |
| Predicate | languageFamilyTargeted |
P46510
|
FINISHED |
| Object | Sinitic languages |
—
|
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: Sinitic languages | Statement: [Pe̍h-ōe-jī, languageFamilyTargeted, Sinitic languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageFamilyTargeted Context triple: [Pe̍h-ōe-jī, languageFamilyTargeted, Sinitic languages]
-
A.
languageFamily
Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
-
B.
languageFamilyOf
Indicates that one entity is the language family to which the other entity (a specific language) belongs.
-
C.
languageFamilyConcerned
chosen
Indicates that something is related to, involves, or pertains to a particular language family.
-
D.
languageFamilyCode
Indicates the language family to which a given language belongs, represented by a standardized code.
-
E.
languageFamilyContext
Indicates the broader linguistic family or grouping within which a particular language or linguistic element is situated.
- 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_69ca84730a5081908de282651019bf2f |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd804c859081908c261ad16b501f0d |
completed | April 1, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69cca561e6b0819090aa795f3c3a2083 |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:55 p.m.