Triple
T32896748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liberian general election, 2017 |
E841493
|
entity |
| Predicate | runnerUpPoliticalParty |
P26342
|
FINISHED |
| Object | Unity Party (Liberia) |
—
|
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: Unity Party (Liberia) | Statement: [Liberian general election, 2017, runnerUpPoliticalParty, Unity Party (Liberia)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runnerUpPoliticalParty Context triple: [Liberian general election, 2017, runnerUpPoliticalParty, Unity Party (Liberia)]
-
A.
runnerUpParty
chosen
Indicates the political party that finished in second place in an election or contest.
-
B.
runnerUpPoliticalPosition
Indicates that an entity finished in second place (runner-up) in a specified political position or election for that position.
-
C.
presidentialRunnerUpParty
Indicates the political party of the candidate who finished second in a presidential election.
-
D.
popularVoteRunnerUp
Indicates that one entity is the candidate who received the second-highest number of votes in a popular vote for the other entity’s election or contest.
-
E.
ledPoliticalPartyInElection
Indicates that an entity served as the leader or head figure of a political party during a specific 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_69f34945ae408190b72d8118c83beb77 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d26f27dc8190ae426a3e1573933e |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:18 a.m.