Triple
T31546009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean-Paul Akayesu |
E804873
|
entity |
| Predicate | perpetratedCrimesIn |
P171954
|
FINISHED |
| Object | Taba commune |
—
|
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: Taba commune | Statement: [Jean-Paul Akayesu, perpetratedCrimesIn, Taba commune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perpetratedCrimesIn Context triple: [Jean-Paul Akayesu, perpetratedCrimesIn, Taba commune]
-
A.
committedCrime
Indicates that an entity has carried out or been responsible for a criminal act or offense.
-
B.
perpetratorOfCrimeAgainst
Indicates that one entity is the person or group responsible for committing a crime against another entity.
-
C.
crimeType
Indicates the specific category or nature of the crime associated with an event or entity.
-
D.
crimeCharged
Indicates that legal authorities have formally accused an entity of committing a specific crime.
-
E.
crimeListedInArticleIII
Indicates that a particular crime is one of the offenses expressly mentioned in Article III of the relevant constitution or legal document.
- 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_69f348d11a048190a65eb8384a3754ac |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a956e9b08190bf83547bba8e8147 |
completed | May 3, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69f6a75656e081908739ed9e2f600e42 |
completed | May 3, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f6a8036ab481908019f2f071fa406e |
completed | May 3, 2026, 1:42 a.m. |
Created at: April 30, 2026, 10:08 p.m.