Triple
T25716872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French presidential elections |
E644885
|
entity |
| Predicate | earlyElectionCause |
P95327
|
FINISHED |
| Object | vacancy of the presidency |
—
|
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: vacancy of the presidency | Statement: [French presidential elections, earlyElectionCause, vacancy of the presidency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlyElectionCause Context triple: [French presidential elections, earlyElectionCause, vacancy of the presidency]
-
A.
reasonForEarlyElection
chosen
Indicates that one event, condition, or circumstance serves as the cause or justification for an early election being held.
-
B.
wasEarlyElection
Indicates that an election was held earlier than its originally scheduled or expected date.
-
C.
byElectionReason
Indicates the reason or cause for which a by-election is being held.
-
D.
usedForEarlyElection
Indicates that something serves as a means or mechanism to trigger or conduct an election earlier than originally scheduled.
-
E.
abolishedBeforeElection
Indicates that something (such as a law, policy, or institution) was formally ended or eliminated prior to a specified election.
- 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_69e77e8476fc8190bd5e9d05b89fad0a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f600c18a14819081b5914dd3b0f9cf |
completed | May 2, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 21, 2026, 9:44 p.m.