Triple
T31688768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jamaican general election, 2016 |
E808729
|
entity |
| Predicate | PNPStatusBeforeElection |
P39368
|
FINISHED |
| Object | governing party |
—
|
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: governing party | Statement: [Jamaican general election, 2016, PNPStatusBeforeElection, governing party]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: PNPStatusBeforeElection Context triple: [Jamaican general election, 2016, PNPStatusBeforeElection, governing party]
-
A.
positionBeforeElection
Indicates that an entity held a particular position or office prior to a specified election.
-
B.
incumbentBeforeElection
Indicates that the subject was already holding the relevant office or position prior to the specified election.
-
C.
mainOppositionBeforeElection
chosen
Indicates that one political entity serves as the primary opposing force to another in the period leading up to an election.
-
D.
speakerBeforeElection
Indicates that the person served as a speaker or spokesperson prior to an election event.
-
E.
preElectionEvent
Indicates an event or activity that occurs in the period leading up to an election, typically related to campaigning, preparation, or election-related processes.
- 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_69f348ddcbc48190950cabcc25ff29b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:07 p.m.