Triple
T37409670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jun-fan |
E929526
|
entity |
| Predicate | hasBearerCitizenship |
P98308
|
FINISHED |
| Object | Hong Kong |
—
|
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: Hong Kong | Statement: [Jun-fan, hasBearerCitizenship, Hong Kong]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBearerCitizenship Context triple: [Jun-fan, hasBearerCitizenship, Hong Kong]
-
A.
hasTypicalCitizenship
Indicates that an entity is generally or commonly a citizen of a specified country or jurisdiction.
-
B.
isCitizenOf
chosen
Indicates that a person holds legal nationality or citizenship status in a particular country or state.
-
C.
hasHostCitizenship
Indicates that an entity holds citizenship in, or is a citizen of, a specified host country or jurisdiction.
-
D.
hasAncestralCitizenshipOf
Indicates that an entity holds or is recognized as holding citizenship of another entity based on ancestral or lineage connections rather than solely on birth or residence.
-
E.
hasCitizenshipRestriction
Indicates that there is a legal or policy-based limitation on who can obtain or hold citizenship in a given context.
- 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_69fd44474ed48190ac372e4c88d762ed |
completed | May 8, 2026, 2:02 a.m. |
| PD | Predicate disambiguation | batch_69fd41ef28a48190a66959be5c964461 |
completed | May 8, 2026, 1:52 a.m. |
Created at: May 3, 2026, 4:16 p.m.