Triple
T31150901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Dakota congressional delegation |
E794066
|
entity |
| Predicate | senateRepresentationType |
P14821
|
FINISHED |
| Object | two senators per state |
—
|
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: two senators per state | Statement: [South Dakota congressional delegation, senateRepresentationType, two senators per state]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: senateRepresentationType Context triple: [South Dakota congressional delegation, senateRepresentationType, two senators per state]
-
A.
federalRepresentationType
Indicates the type or form of representation an entity has within a federal governmental or legislative structure.
-
B.
representedInSenate
Indicates that an entity serves as a representative for another entity within a senate or upper legislative chamber.
-
C.
natureOfRepresentation
Indicates the manner or form in which something is represented or depicted in relation to something else.
-
D.
senateRepresentationBasis
chosen
Indicates the principle or criteria on which representation in a senate is allocated or determined.
-
E.
numberOfRepresentatives
Indicates the quantity of representatives associated with a given entity or unit.
- 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_69f224d41bb48190a5621cd1485e3a30 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6c1bb5f248190834161b5a6ba1ece |
completed | May 3, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: April 29, 2026, 9:06 p.m.