Triple
T27113617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 马思纯 |
E686779
|
entity |
| Predicate | 国别身份 |
P138160
|
FINISHED |
| Object | 中国内地 |
—
|
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: 中国内地 | Statement: [马思纯, 国别身份, 中国内地]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 国别身份 Context triple: [马思纯, 国别身份, 中国内地]
-
A.
nationalityInCoverIdentity
Indicates that an entity’s assumed or cover identity is associated with a particular nationality.
-
B.
身分
Indicates a relationship where an entity holds a particular social, legal, or role-based status or identity in relation to a group, institution, or context.
-
C.
nationalityOrGroup
chosen
Indicates that an entity belongs to, is associated with, or is identified as a member of a particular nation, ethnic group, or cultural community.
-
D.
countryOfCitizenship
Indicates the country in which a person or entity holds legal citizenship.
-
E.
nationalityMattersReservedTo
Indicates that a matter or issue is reserved specifically to the competence or authority of a particular nationality.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6240450088190af486dbde3daeacb |
completed | May 2, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 8:55 a.m.