Triple
T27706591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pass Laws in South Africa |
E698572
|
entity |
| Predicate | siteOfMajorProtest |
P3165
|
FINISHED |
| Object | Soweto |
—
|
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: Soweto | Statement: [Pass Laws in South Africa, siteOfMajorProtest, Soweto]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: siteOfMajorProtest Context triple: [Pass Laws in South Africa, siteOfMajorProtest, Soweto]
-
A.
locationOfNotableProtest
chosen
Indicates the place where a significant or notable protest event occurred.
-
B.
notableProtest
Indicates that an entity is recognized for having led, organized, or been centrally involved in a significant protest or demonstration.
-
C.
protestFocus
Indicates that a protest is directed toward, concerned with, or centered on a particular issue, target, or subject.
-
D.
numberOfProtesters
Indicates the total count of individuals participating as protesters in a given event or context.
-
E.
protests
Indicates that an entity publicly expresses opposition or disapproval toward another entity, action, or situation.
- 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_69ef590f655c81909f93893b3b3219b2 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6895f0819088655277e45859a8 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 3 p.m.