Triple
T25238119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Callaghan government |
E632390
|
entity |
| Predicate | confidenceVoteMargin |
P129855
|
FINISHED |
| Object | Lost by one vote |
—
|
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: Lost by one vote | Statement: [Callaghan government, confidenceVoteMargin, Lost by one vote]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: confidenceVoteMargin Context triple: [Callaghan government, confidenceVoteMargin, Lost by one vote]
-
A.
approvalVoteMargin
Indicates the numerical difference between the number of approval votes received and a comparison threshold or opposing votes in a decision or election.
-
B.
popularVoteMargin
Indicates the difference in the number or percentage of popular votes received by two candidates or options in an election.
-
C.
marginOfVictoryElectoralVotes
Indicates the difference in the number of electoral votes between the winning and losing candidates or parties in an election.
-
D.
typicalPartyMargin
Indicates the usual or characteristic difference in support or vote share between political parties in a given context.
-
E.
defeatedByMargin
chosen
Indicates that one entity was defeated by another with a specified numerical margin or difference in score, votes, or performance.
- 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_69e75a8ec5f88190b9eba06ae42b413a |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:07 p.m.