Triple
T24474886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Đỗ Mười |
E617204
|
entity |
| Predicate | headOfPoliticalParty |
P9178
|
FINISHED |
| Object | Communist Party of Vietnam |
—
|
NE NERFINISHED |
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: Communist Party of Vietnam | Statement: [Đỗ Mười, headOfPoliticalParty, Communist Party of Vietnam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headOfPoliticalParty Context triple: [Đỗ Mười, headOfPoliticalParty, Communist Party of Vietnam]
-
A.
politicalPartyLeader
chosen
Indicates that one entity serves as the leader or head of a specified political party.
-
B.
monarchOfParty
Indicates that one entity is the reigning monarch who is formally associated with, or represents, a particular political party.
-
C.
partyGovernmentLeader
Indicates that the person is the leader of a political party that is currently forming or heading the government.
-
D.
majorParty4Leader
Indicates that the subject is the leader of a fourth major political party in a given political system or context.
-
E.
largestPartyLeader
Indicates that the subject is the leader of the largest political party within a given political body or 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_69e2d7f197588190889a03e620558059 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29947084081908895573a4a4e4822 |
completed | April 29, 2026, 11:50 p.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:20 a.m.