Triple
T24264437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winnie Madikizela-Mandela |
E604799
|
entity |
| Predicate | termStartAsDeputyMinister |
P155379
|
FINISHED |
| Object | 1994 |
—
|
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: 1994 | Statement: [Winnie Madikizela-Mandela, termStartAsDeputyMinister, 1994]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termStartAsDeputyMinister Context triple: [Winnie Madikizela-Mandela, termStartAsDeputyMinister, 1994]
-
A.
termStartAsMinisterGeneral
Indicates the date or point in time when an individual begins serving in the role of Minister General.
-
B.
termAsMinisterStart
Indicates the date or point in time when an individual begins serving in a specific ministerial position.
-
C.
termStartAsDelegate
Indicates that an entity begins its role or service in a delegate capacity at a specified starting point or time.
-
D.
termStartAsActingPrimeMinister
Indicates that a person’s term in office begins specifically in the capacity of acting prime minister, rather than as a fully appointed or elected prime minister.
-
E.
deputyPrimeMinisterStart
Indicates the date or point in time when an individual begins serving in the role of deputy prime minister.
- 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_69e29544c29c8190b023606eafe5d36a |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28c6a4cc88190914f1c52567d613a |
completed | April 29, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69f1c450aa508190bc9d372a5f6ee47a |
completed | April 29, 2026, 8:41 a.m. |
| PDg | Predicate description generation | batch_69f1c6d4e99081909f61899eccafb73e |
completed | April 29, 2026, 8:52 a.m. |
Created at: April 18, 2026, 12:06 a.m.