Triple
T7845593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African general elections |
E181914
|
entity |
| Predicate | seatAllocationFormula |
P47248
|
FINISHED |
| Object | largest remainder method |
—
|
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: largest remainder method | Statement: [South African general elections, seatAllocationFormula, largest remainder method]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seatAllocationFormula Context triple: [South African general elections, seatAllocationFormula, largest remainder method]
-
A.
seatAllocationLevel
Indicates the degree or priority level at which seats are assigned or distributed among eligible entities.
-
B.
seatsAreAllocatedTo
Indicates that specific seats are assigned or designated to particular entities (such as people, groups, or bookings).
-
C.
seatNotationSystem
Indicates the system or convention used to label, number, or otherwise denote seats within a venue or vehicle.
-
D.
seatsAllocatedBy
chosen
Indicates that seats are assigned or distributed by a particular agent, authority, or mechanism.
-
E.
remainingSeatsAllocation
Indicates how any seats that are still unassigned after an initial distribution are allocated among eligible parties or entities.
- 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_69ca8285d6488190a95d4c02d7354b53 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb163d92fc8190a4efcb08d6b3d404 |
completed | March 31, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69cae92180f88190ae3d44c3de7adc93 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:49 p.m.