Triple
T1894560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dominican Civil War |
E41948
|
entity |
| Predicate | statedU.S.Objective |
P677
|
FINISHED |
| Object | prevention of a second Cuba |
—
|
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: prevention of a second Cuba | Statement: [Dominican Civil War, statedU.S.Objective, prevention of a second Cuba]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statedU.S.Objective Context triple: [Dominican Civil War, statedU.S.Objective, prevention of a second Cuba]
-
A.
objectiveOfUnitedStates
chosen
Indicates that something is an official objective or goal pursued by the United States.
-
B.
UnionObjective
Indicates that an entity has the goal, purpose, or objective of forming, maintaining, or advancing a union or unified organization.
-
C.
nationalGoals
Indicates a relationship where certain objectives or targets are officially set or recognized as the goals of a nation.
-
D.
statedAsGoalFor
Indicates that something has been explicitly declared or identified as a goal for a particular entity or context.
-
E.
strategicGoal
Indicates that one entity represents a long-term objective or desired outcome that another entity is intentionally aiming to achieve or align actions toward.
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb16c09e48190a345c95eab59fd87 |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe7e7e88190b58c0df59187c0c2 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.