Triple
T9537257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prosecutor v. Jean-Paul Akayesu |
E230048
|
entity |
| Predicate | roleOfDefendant |
P16985
|
FINISHED |
| Object | mayor of Taba commune |
—
|
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: mayor of Taba commune | Statement: [Prosecutor v. Jean-Paul Akayesu, roleOfDefendant, mayor of Taba commune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOfDefendant Context triple: [Prosecutor v. Jean-Paul Akayesu, roleOfDefendant, mayor of Taba commune]
-
A.
defendant
Indicates that an entity is the party accused or sued in a legal action or proceeding.
-
B.
coDefendant
Indicates that two or more parties are jointly named and involved as defendants in the same legal case or proceeding.
-
C.
defendantPosition
Indicates the role, stance, or location that a defendant holds within a legal case or proceeding.
-
D.
defendantStatus
Indicates the legal condition or standing of a defendant within a judicial or law-enforcement process.
-
E.
legalCaseRole
chosen
Indicates the specific role or capacity an entity holds within a legal case, such as plaintiff, defendant, judge, or attorney.
- 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.