Triple
T25286827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Dakota House of Representatives |
E633963
|
entity |
| Predicate | electsFromEachDistrict |
P38391
|
FINISHED |
| Object | 2 representatives |
—
|
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: 2 representatives | Statement: [North Dakota House of Representatives, electsFromEachDistrict, 2 representatives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electsFromEachDistrict Context triple: [North Dakota House of Representatives, electsFromEachDistrict, 2 representatives]
-
A.
eachDistrictElects
chosen
Indicates that every electoral district selects or chooses its own representative or set of representatives.
-
B.
electsRepresentativeEvery
Indicates that one entity periodically chooses or votes to select another entity to serve as its representative.
-
C.
eachStateAndRegionElects
Indicates that every state and region is responsible for choosing or voting for a particular representative, body, or position.
-
D.
electoralCollegeDistrictOf
Indicates that one entity is the electoral college district to which another entity (such as a voter, candidate, or geographic area) belongs or is assigned.
-
E.
numberOfElectors
Indicates the total count of electors associated with a given entity or context.
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f657f653448190a945b4751af8507d |
completed | May 2, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 21, 2026, 1:19 p.m.