Triple
T9792550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somoza dictatorship |
E237638
|
entity |
| Predicate | repressionTargets |
P18600
|
FINISHED |
| Object | political opposition |
—
|
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 opposition | Statement: [Somoza dictatorship, repressionTargets, political opposition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repressionTargets Context triple: [Somoza dictatorship, repressionTargets, political opposition]
-
A.
oppositionTargeted
Indicates that an action or strategy is specifically directed against or aimed at an opposing party, group, or viewpoint.
-
B.
repressedDissent
chosen
Indicates that one party has actively suppressed or stifled opposition, criticism, or disagreement from another party or group.
-
C.
aimsToEliminate
Indicates an intention or directed effort by one entity to remove, destroy, or completely get rid of another entity or condition.
-
D.
lawEnforcementTarget
Indicates that an entity is the focus or object of attention, investigation, or action by law enforcement authorities.
-
E.
targetedRegime
Indicates that an entity intentionally directed actions, policies, or operations against a particular governing regime.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda346945481908c2698a79c578ef5 |
completed | April 1, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69cd03da45a88190b71b1be3354c15a6 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:28 p.m.