Triple
T37387446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matanza del Río Sumpul |
E928606
|
entity |
| Predicate | hasHumanRightsViolationType |
P14172
|
FINISHED |
| Object | extrajudicial killing |
—
|
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: extrajudicial killing | Statement: [Matanza del Río Sumpul, hasHumanRightsViolationType, extrajudicial killing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHumanRightsViolationType Context triple: [Matanza del Río Sumpul, hasHumanRightsViolationType, extrajudicial killing]
-
A.
stanceOnHumanRightsRecord
Indicates the position or evaluation an entity holds regarding another entity’s human rights record.
-
B.
hasTypeOfViolence
chosen
Indicates that an entity involves, exhibits, or is characterized by a specific kind or category of violent behavior or action.
-
C.
hasTypeOfVictims
Indicates that an entity is associated with victims of a specified type or category.
-
D.
humanRightsConcern
Indicates a situation, action, or condition that raises issues related to the recognition, protection, or violation of human rights.
-
E.
violationOf
Indicates that one entity breaches, disobeys, or infringes upon a rule, law, agreement, or right associated with 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_69f76eb9e66881908534cf22d04c3b5a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbbc49da8c8190902bbb05d2477cab |
completed | May 6, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69fbb13f34b08190bbbb220ac1e6e666 |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:16 p.m.