Triple
T37826943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 United States House of Representatives elections |
E943086
|
entity |
| Predicate | afterElectionSpeaker |
P89280
|
FINISHED |
| Object | Paul Ryan |
—
|
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: Paul Ryan | Statement: [2016 United States House of Representatives elections, afterElectionSpeaker, Paul Ryan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afterElectionSpeaker Context triple: [2016 United States House of Representatives elections, afterElectionSpeaker, Paul Ryan]
-
A.
speakerAfterElection
chosen
Indicates that an individual holds or assumes the role of speaker after an election has taken place.
-
B.
afterElectionSenator
Indicates that one person holds the position of senator following a specified election.
-
C.
endedAfterElection
Indicates that the referenced event or state concluded after an election had taken place.
-
D.
vicePresidentAfterElection
Indicates that one person holds the office of vice president following a specified election or electoral event.
-
E.
statePresidentAfterElection
Indicates that an individual becomes the president of a state as a result of a specific election, serving in that role after the election has taken place.
- 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_69f76eea4c8c8190a335aed5955cf2db |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.