Triple
T24730328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2007 French presidential election |
E618264
|
entity |
| Predicate | centristCandidate |
P157692
|
FINISHED |
| Object | François Bayrou |
—
|
NE NERFINISHED |
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: François Bayrou | Statement: [2007 French presidential election, centristCandidate, François Bayrou]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centristCandidate Context triple: [2007 French presidential election, centristCandidate, François Bayrou]
-
A.
featuredCandidate
Indicates that a particular candidate is highlighted or given special prominence relative to others.
-
B.
capitalCandidate
Indicates that an entity is being considered or proposed as the capital of a given region or political unit.
-
C.
democraticNominationContender
Indicates that an entity is a candidate actively competing for the Democratic Party’s nomination for a particular political office.
-
D.
firstBallotCandidate
Indicates that the entity was a candidate in the first ballot of an election or selection process.
-
E.
electedCandidate
Indicates that a particular person has been chosen as the winner in an election for a given position or office.
- F. None of above. chosen
Provenance (4 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_69e2fab772608190b74163751047ff50 |
completed | April 18, 2026, 3:29 a.m. |
| NER | Named-entity recognition | batch_69f44a417a58819081777e18dda149fd |
completed | May 1, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69f442a977b08190b44eac040cb90211 |
completed | May 1, 2026, 6:05 a.m. |
| PDg | Predicate description generation | batch_69f44a3adb7c8190941572f718b3b93c |
completed | May 1, 2026, 6:37 a.m. |
Created at: April 18, 2026, 4:02 a.m.