Triple
T11148658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yemen–United States relations |
E263729
|
entity |
| Predicate | USPolicyTool |
P98066
|
FINISHED |
| Object | economic aid |
—
|
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 aid | Statement: [Yemen–United States relations, USPolicyTool, economic aid]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: USPolicyTool Context triple: [Yemen–United States relations, USPolicyTool, economic aid]
-
A.
analyzesPolicyTool
Indicates that one entity examines, evaluates, or studies a policy-related tool or instrument to understand its features, effectiveness, or implications.
-
B.
coordinatesNationalPoliciesFor
Indicates that one entity organizes and harmonizes national-level policies or strategies across multiple actors or domains.
-
C.
relatedLegislation
Indicates that there exists a legislative document that is connected to, affects, or is otherwise relevant to the subject entity.
-
D.
governmentAction
Indicates actions, decisions, or interventions carried out by a government or its agencies in relation to other entities.
-
E.
counselForUnitedStates
Indicates that an entity serves as legal counsel representing the United States in a legal or official capacity.
- F. None of above. chosen
Provenance (4 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8701ea481908c86c2359f5dc957 |
completed | April 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69d75ce71944819089eee9b5c9283cbd |
completed | April 9, 2026, 8:01 a.m. |
| PDg | Predicate description generation | batch_69d7706116248190a87440bec3960884 |
completed | April 9, 2026, 9:24 a.m. |
Created at: April 8, 2026, 9:28 p.m.