Triple
T28499461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Vorster Square |
E721193
|
entity |
| Predicate | causeOfDeathControversy |
P67150
|
FINISHED |
| Object | alleged suicides of detainees |
—
|
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: alleged suicides of detainees | Statement: [John Vorster Square, causeOfDeathControversy, alleged suicides of detainees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfDeathControversy Context triple: [John Vorster Square, causeOfDeathControversy, alleged suicides of detainees]
-
A.
causeOfDeath
Indicates the specific factor, event, or condition that directly resulted in an entity’s death.
-
B.
debatedAsCauseOf
Indicates that one entity is discussed or argued over as a possible cause or origin of another entity.
-
C.
deathCauseUncertainty
chosen
Indicates that there is ambiguity, doubt, or lack of definitive information about the cause of death in the relationship being described.
-
D.
reasonForDeath
Indicates the cause, circumstance, or condition that led to an entity’s death.
-
E.
namedAfterCauseOfDeath
Indicates that an entity is named after the cause of death of a person or organism.
- 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_69f01a5afdac8190ac6e72d5c100bd58 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d26ceb08819091c71c001e954936 |
completed | May 3, 2026, 4:43 a.m. |
Created at: April 28, 2026, 3:06 a.m.