Triple
T8179138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Zealand general elections |
E191013
|
entity |
| Predicate | previousSystem |
P9736
|
FINISHED |
| Object | first-past-the-post voting |
—
|
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: first-past-the-post voting | Statement: [New Zealand general elections, previousSystem, first-past-the-post voting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousSystem Context triple: [New Zealand general elections, previousSystem, first-past-the-post voting]
-
A.
predecessorSystem
chosen
Indicates that one system existed or was in use before and was replaced or superseded by another system.
-
B.
previousSystemClosed
Indicates that a prior system, session, or process has been properly terminated or closed before the current context.
-
C.
previousFileSystem
Indicates that one file system existed or was in use before another file system in a temporal or versioning sequence.
-
D.
previousMode
Indicates that one mode directly precedes another in a sequence or state transition.
-
E.
predecessorSystemType
Indicates that one system type functioned as the predecessor or earlier version to another system type.
- 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_69ca82c4538081909404325aa5639483 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4abd9768819091298e4dd995ac96 |
completed | March 31, 2026, 4:17 a.m. |
| PD | Predicate disambiguation | batch_69cb36a7952481908f34e3e82f375a84 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:40 p.m.