Triple
T28905571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Van Drew |
E733065
|
entity |
| Predicate | partySwitchContext |
P38460
|
FINISHED |
| Object | switched parties during the 116th United States Congress |
—
|
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: switched parties during the 116th United States Congress | Statement: [Jeff Van Drew, partySwitchContext, switched parties during the 116th United States Congress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partySwitchContext Context triple: [Jeff Van Drew, partySwitchContext, switched parties during the 116th United States Congress]
-
A.
partySwitch
chosen
Indicates that an entity changes its affiliation from one political party to another.
-
B.
partyStatusContext
Indicates the contextual status or role a party holds within a specific situation, event, or legal/transactional framework.
-
C.
conferenceChangeContext
Indicates a change in the state, scope, or parameters of a conference-related interaction or session.
-
D.
switching
Indicates changing from one state, option, or entity to another, replacing the original with a different one.
-
E.
switchesPlacesWith
Indicates that two entities exchange their respective positions or roles with each other.
- 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_69f05b096d208190958a57d2e4b5a93a |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 28, 2026, 8:07 a.m.