Triple
T22646333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilles Duceppe |
E558973
|
entity |
| Predicate | electionTypeContested |
P89413
|
FINISHED |
| Object | Canadian federal election |
—
|
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: Canadian federal election | Statement: [Gilles Duceppe, electionTypeContested, Canadian federal election]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electionTypeContested Context triple: [Gilles Duceppe, electionTypeContested, Canadian federal election]
-
A.
hasOfficeContested
Indicates that an individual has been a candidate for a particular public office in an election.
-
B.
wasContestedBetween
Indicates that an event, position, or resource was the subject of competition or dispute involving two or more opposing parties.
-
C.
electionContests
Indicates that one election is in competition with, or formally challenges the outcome or validity of, another election.
-
D.
controlContested
Indicates that authority or dominance over something is disputed or challenged between two or more parties.
-
E.
typeOfElectionContested
chosen
Indicates the specific kind or category of election in which an entity is competing or has competed.
- 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_69e24547f7fc819086e2c4ba3b979657 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f170382ba48190b77692762db43313 |
completed | April 29, 2026, 2:43 a.m. |
| PD | Predicate disambiguation | batch_69ee6294c4c08190b7e4829f4b9af24b |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:05 p.m.