Triple
T11897604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Foreign Military Financing |
E283073
|
entity |
| Predicate | oftenConditionedOn |
P19751
|
FINISHED |
| Object | political and economic reforms |
—
|
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: political and economic reforms | Statement: [U.S. Foreign Military Financing, oftenConditionedOn, political and economic reforms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenConditionedOn Context triple: [U.S. Foreign Military Financing, oftenConditionedOn, political and economic reforms]
-
A.
contingentOn
chosen
Indicates that the occurrence, validity, or outcome of one event or condition depends on the fulfillment or existence of another.
-
B.
holdsUnderCondition
Indicates that one fact, rule, or relationship remains valid only when a specified condition or set of conditions is satisfied.
-
C.
presentCondition
Indicates that an entity currently has or exhibits a particular state, situation, or condition.
-
D.
oftenPrecededBy
Indicates that one event, state, or item commonly occurs or appears before another in time or sequence.
-
E.
oftenStatedWith
Indicates that one statement, fact, or expression is frequently mentioned or asserted together with another.
- 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_69d6ab2a90b08190a4e818821cc93e6d |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8dd13cc10819089d8d5103e562924 |
completed | April 10, 2026, 11:20 a.m. |
| PD | Predicate disambiguation | batch_69d8bb2fca4481909893f3428b0871ac |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:44 p.m.