Triple
T17372028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | pan-Blue Coalition |
E422338
|
entity |
| Predicate | policyPreference |
P60489
|
FINISHED |
| Object | economic integration with mainland 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: economic integration with mainland China | Statement: [pan-Blue Coalition, policyPreference, economic integration with mainland China]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyPreference Context triple: [pan-Blue Coalition, policyPreference, economic integration with mainland China]
-
A.
typicalPolicyPreference
Indicates that one entity’s policy preference is characteristic or representative of what is usually favored by another entity or group.
-
B.
statedPreference
chosen
Indicates that one entity has explicitly expressed or declared a preference for another entity or option.
-
C.
unitPreference
Indicates a relationship where one entity specifies or favors a particular unit of measurement or representation over others.
-
D.
decisionPublicationPolicy
Indicates the policy or rules governing how decisions are made public or communicated.
-
E.
licensePreference
Indicates a party’s chosen or prioritized type of license to use, grant, or operate under 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a69d93c81908ce2d909857a3a11 |
completed | April 19, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69e3b02ac8688190a7182f1b2151d721 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.