Triple
T38029513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | military regime of Raoul Cédras |
E948868
|
entity |
| Predicate | usedParamilitaryGroup |
P4347
|
FINISHED |
| Object | FRAPH |
—
|
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: FRAPH | Statement: [military regime of Raoul Cédras, usedParamilitaryGroup, FRAPH]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedParamilitaryGroup Context triple: [military regime of Raoul Cédras, usedParamilitaryGroup, FRAPH]
-
A.
paramilitary
Indicates that an entity is associated with an organized, armed group that operates similarly to a military force but is not part of the official state military.
-
B.
paramilitaryRole
Indicates that an entity serves in, is associated with, or performs functions for a paramilitary organization or unit.
-
C.
paramilitaryWing
chosen
Indicates that one entity functions as the paramilitary or armed wing associated with another entity, typically an organization or movement.
-
D.
usesMilitaryUnit
Indicates that one entity employs, deploys, or otherwise makes operational use of a specific military unit.
-
E.
usesMilitarySystemSimilarTo
Indicates that one entity employs a military system that is comparable in structure, doctrine, or operational methods to that of another entity.
- 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_69f76efd1bc48190a729097fe5177b61 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc99890888190ad8a2f3b8c7adf34 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.