Triple
T9537002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Appeals Chamber (ICTR) |
E230042
|
entity |
| Predicate | canRevise |
P48269
|
FINISHED |
| Object | trial judgment |
—
|
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: trial judgment | Statement: [Appeals Chamber (ICTR), canRevise, trial judgment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canRevise Context triple: [Appeals Chamber (ICTR), canRevise, trial judgment]
-
A.
revisionOf
Indicates that one entity is a modified or updated version of another earlier entity.
-
B.
mayAmend
chosen
Indicates that one party has the authority or permission to modify, revise, or change something that already exists.
-
C.
canRepeal
Indicates that one entity has the authority or power to revoke, annul, or cancel a rule, decision, or action established by another entity.
-
D.
canReview
Indicates that one entity has the permission or ability to evaluate, assess, or provide feedback on another entity.
-
E.
canBeCorrectedBy
Indicates that something has the potential to be made accurate, fixed, or improved through the intervention or action of a specified agent or method.
- 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_69ca847b1b3081908f72bc932c17cc41 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98ce884c8190a8b3c2dc7c73c2c9 |
completed | April 1, 2026, 10:14 p.m. |
| PD | Predicate disambiguation | batch_69cca56c44f88190a54a5d2a133bb07e |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 8:01 p.m.