Triple
T23016123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Xia |
E573031
|
entity |
| Predicate | rightsSituation |
P12239
|
FINISHED |
| Object | restrictions on freedom of movement in China |
—
|
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: restrictions on freedom of movement in China | Statement: [Liu Xia, rightsSituation, restrictions on freedom of movement in China]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rightsSituation Context triple: [Liu Xia, rightsSituation, restrictions on freedom of movement in China]
-
A.
rightsImplicated
Indicates that certain rights are affected, challenged, or brought into question as a consequence of the related action or relationship.
-
B.
rights
Indicates that an entity possesses entitlements, permissions, or legal/moral claims in relation to another entity or context.
-
C.
positionOnRights
Indicates a stance, opinion, or policy an entity holds regarding rights (such as legal, human, or civil rights).
-
D.
rightsCategory
Indicates the classification or type of rights associated with an entity or relationship.
-
E.
humanRightsSituation
chosen
Indicates the overall condition, treatment, and respect for individuals’ fundamental rights and freedoms within a given context or jurisdiction.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e4dcd48190b2b1c2ab43205e41 |
completed | April 29, 2026, 4:07 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:51 p.m.