Triple
T3113060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Truth and Reconciliation Commission (South Africa) |
E64994
|
entity |
| Predicate | reportedNumberOfVictimStatements |
P26914
|
FINISHED |
| Object | over 21,000 |
—
|
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 21,000 | Statement: [Truth and Reconciliation Commission (South Africa), reportedNumberOfVictimStatements, over 21,000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reportedNumberOfVictimStatements Context triple: [Truth and Reconciliation Commission (South Africa), reportedNumberOfVictimStatements, over 21,000]
-
A.
estimatedVictimsUnderAuthority
Indicates that a specified authority is estimated to have a certain number of victims under its control, influence, or jurisdiction.
-
B.
portraysAsVictim
Indicates that one entity represents or depicts another entity as a victim in a given context or narrative.
-
C.
numberOfSuspectedVictims
Indicates the count of individuals believed or alleged to be victims in a particular incident, case, or context.
-
D.
hasVictimCount
chosen
Indicates the number of victims associated with a particular event, action, or entity.
-
E.
coVictim
Indicates that two or more entities are victims in the same harmful event or incident.
- 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_69ad857fcc088190b0c4d45a5cde6f61 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada43c79448190aa72f707319e8c5e |
completed | March 8, 2026, 4:30 p.m. |
| PD | Predicate disambiguation | batch_69ad9df25d4c81908ff0f6cff55d0563 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:04 p.m.