Triple
T37409680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jun-fan |
E929526
|
entity |
| Predicate | hasBearerPrimaryLanguage |
P83252
|
FINISHED |
| Object | Cantonese |
—
|
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: Cantonese | Statement: [Jun-fan, hasBearerPrimaryLanguage, Cantonese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBearerPrimaryLanguage Context triple: [Jun-fan, hasBearerPrimaryLanguage, Cantonese]
-
A.
hasPrimaryLanguage1
chosen
Indicates that an entity’s main or most commonly used language is the specified language.
-
B.
hasPrimaryLanguageDialect
Indicates that an entity’s main or default language is a specific dialect of a broader language.
-
C.
hasPrimaryVernacularLanguageFamily
Indicates that an entity’s main vernacular language belongs to a specified language family.
-
D.
hasPrimaryLanguageBranch
Indicates that an entity’s main or dominant language belongs to a specified language branch or family.
-
E.
hasPrimaryLanguageSubbranch
Indicates that one language subbranch is the main or principal subbranch associated with a given language or language family.
- 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_69f76ebde49481908566cd96b37ccc84 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: May 3, 2026, 4:16 p.m.