Triple
T180287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese Taipei |
E3857
|
entity |
| Predicate | perceivedBySomeAs |
P1120
|
FINISHED |
| Object | undermining Taiwan sovereignty |
—
|
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: undermining Taiwan sovereignty | Statement: [Chinese Taipei, perceivedBySomeAs, undermining Taiwan sovereignty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perceivedBySomeAs Context triple: [Chinese Taipei, perceivedBySomeAs, undermining Taiwan sovereignty]
-
A.
hasPerception
Indicates that one entity is aware of, senses, or recognizes another entity or phenomenon.
-
B.
considered
chosen
Indicates that one entity regards, judges, or thinks about another entity in a particular way or context.
-
C.
characterizedBy
Indicates that one entity possesses a defining quality, feature, or attribute expressed by another entity.
-
D.
observedBy
Indicates that an entity is perceived, monitored, or recorded by another entity acting as the observer.
-
E.
interpretedAs
Indicates that something is understood, perceived, or taken to mean something else, often based on context or subjective judgment.
- 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_69a25497e2f08190a040f8c6e1842643 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a25901a9188190b8f510bec8c8e7f2 |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a2566ccc288190add5624ede96d82b |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:40 a.m.