Triple
T28256892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French presidential election, 2012 |
E712472
|
entity |
| Predicate | firstRoundCandidate |
P106110
|
FINISHED |
| Object | François Hollande |
—
|
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 Hollande | Statement: [French presidential election, 2012, firstRoundCandidate, François Hollande]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstRoundCandidate Context triple: [French presidential election, 2012, firstRoundCandidate, François Hollande]
-
A.
firstRoundLeadingCandidate
Indicates that the subject is the candidate who is leading in vote count after the first round of an election or selection process.
-
B.
firstBallotCandidate
chosen
Indicates that the entity was a candidate in the first ballot of an election or selection process.
-
C.
secondRoundCandidate
Indicates that an entity has advanced past an initial selection stage and is being considered as a candidate in a second round of evaluation or decision-making.
-
D.
firstRound
Indicates that the referenced event, match, or interaction occurs in the initial or opening round of a multi-round process or competition.
-
E.
firstRoundFourthPlaceCandidate
Indicates that the referenced candidate finished in fourth place in the first round of a multi-round selection or competition process.
- 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_69efb5207eb08190827e4c34048030b1 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69ffde9263248190996f970b6cf6e49d |
completed | May 10, 2026, 1:25 a.m. |
| PD | Predicate disambiguation | batch_69ffdd760f1c8190abc6c0c1cd97ba5f |
completed | May 10, 2026, 1:20 a.m. |
Created at: April 27, 2026, 11:08 p.m.