Triple
T4048756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Party (South Africa) |
E84131
|
entity |
| Predicate | endTimeOfHeldOffice |
P23665
|
FINISHED |
| Object | 1948 |
—
|
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: 1948 | Statement: [United Party (South Africa), endTimeOfHeldOffice, 1948]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTimeOfHeldOffice Context triple: [United Party (South Africa), endTimeOfHeldOffice, 1948]
-
A.
officeholderEndTime
Indicates the time or date at which a person’s term in a particular office or position comes to an end.
-
B.
endTimeOfPresidency
Indicates the specific time at which a person's term in the presidency concludes.
-
C.
partyLeadershipEndTime
chosen
Indicates the time at which an entity’s leadership role within a political party or organization comes to an end.
-
D.
endTimeAsHeadOfPresidentialAdministration
Indicates the date and time when an individual’s tenure as head of the presidential administration comes to an end.
-
E.
lastOfficeHolderStartDate
Indicates the date on which the most recent person to hold a particular office or position began their term.
- 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_69aed930bd5c819083e7dcc14fc44f69 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb82d1a08190aa8c5c48d368b58b |
completed | March 9, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69aef900386481909d04555a9ec9b0e3 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:37 p.m.