Triple
T32896742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liberian general election, 2017 |
E841493
|
entity |
| Predicate | numberOfPresidentialCandidatesFirstRound |
P203840
|
FINISHED |
| Object | 20 |
—
|
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: 20 | Statement: [Liberian general election, 2017, numberOfPresidentialCandidatesFirstRound, 20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfPresidentialCandidatesFirstRound Context triple: [Liberian general election, 2017, numberOfPresidentialCandidatesFirstRound, 20]
-
A.
numberOfPresidentialRounds
Indicates the total count of distinct terms or periods a person has served as president.
-
B.
numberOfPresidentialCandidatesApproximate
Indicates an approximate count of individuals who are presidential candidates in a given context.
-
C.
firstRoundLeadingCandidate
Indicates that the subject is the candidate who is leading in vote count after the first round of an election or selection process.
-
D.
numberOfPresidentialCampaigns
Indicates the total count of times an individual has run as a candidate in a presidential election.
-
E.
firstBallotCandidate
Indicates that the entity was a candidate in the first ballot of an election or selection process.
- 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_69f34945ae408190b72d8118c83beb77 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a021f84715881908e25b6548e7cf62e |
completed | May 11, 2026, 6:27 p.m. |
| PD | Predicate disambiguation | batch_6a021739b7288190a4ca94c04074c78a |
completed | May 11, 2026, 5:51 p.m. |
| PDg | Predicate description generation | batch_6a021f8366c08190bc790e47b0acc7a9 |
completed | May 11, 2026, 6:27 p.m. |
Created at: May 1, 2026, 1:18 a.m.