Triple
T22533932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fukuda Doctrine |
E557109
|
entity |
| Predicate | hasKeyAudience |
P793
|
FINISHED |
| Object | leaders of ASEAN member states |
—
|
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: leaders of ASEAN member states | Statement: [Fukuda Doctrine, hasKeyAudience, leaders of ASEAN member states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyAudience Context triple: [Fukuda Doctrine, hasKeyAudience, leaders of ASEAN member states]
-
A.
hasAudience
chosen
Indicates that an entity is intended to be received, viewed, or engaged with by a particular group of people.
-
B.
hasKeyClaim
Indicates that one entity contains, presents, or is associated with a central or primary claim expressed by another entity.
-
C.
hasAudienceOrigin
Indicates that an audience is characterized by or associated with a particular geographic, cultural, or demographic origin.
-
D.
hasAudiencePolicy
Indicates that there is a specified rule or policy governing which audience or group is allowed to access, view, or receive something.
-
E.
hasAudienceFormat
Indicates that an entity is associated with a particular format or medium in which its audience receives or experiences it.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed952f48190b63225e7de131679 |
completed | April 29, 2026, 1:28 a.m. |
| PD | Predicate disambiguation | batch_69e898c864148190a3f5feec7967d49c |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:51 p.m.