Triple
T21829970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guatemalan Civil War |
E538964
|
entity |
| Predicate | percentageOfAbusesByStateForces |
P145826
|
FINISHED |
| Object | over 90 percent |
—
|
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: over 90 percent | Statement: [Guatemalan Civil War, percentageOfAbusesByStateForces, over 90 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageOfAbusesByStateForces Context triple: [Guatemalan Civil War, percentageOfAbusesByStateForces, over 90 percent]
-
A.
natureOfAtrocities
Indicates the specific type or character of atrocities associated with an event, action, or entity.
-
B.
isCriminalizedIn
Indicates that a specific behavior, action, or condition is prohibited and subject to legal penalties within a particular jurisdiction or legal system.
-
C.
legalStatusOfVictims
Indicates the legal classification or condition of the victims in relation to the event or action described.
-
D.
numberOfTortureVictims
Indicates the quantity of individuals who have been subjected to torture.
-
E.
persecutionOf
Indicates the act of subjecting an entity to persistent, often unjust hostility, harassment, or oppression, typically on the basis of identity, beliefs, or group membership.
- 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_69e0c475cda88190987d08f23caebdc1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0913554508190b81347f01d3903e8 |
completed | April 28, 2026, 10:51 a.m. |
| PD | Predicate disambiguation | batch_69e6be815a108190be81d7c987d0c0d6 |
completed | April 21, 2026, 12:02 a.m. |
| PDg | Predicate description generation | batch_69e6c670ee608190b9cfdc09de74f0de |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 6:54 p.m.