Triple
T1987605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1964 Indiana Democratic presidential primary |
E43176
|
entity |
| Predicate | levelOfElection |
P26471
|
FINISHED |
| Object | state-level |
—
|
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: state-level | Statement: [1964 Indiana Democratic presidential primary, levelOfElection, state-level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: levelOfElection Context triple: [1964 Indiana Democratic presidential primary, levelOfElection, state-level]
-
A.
electorateLevel
chosen
Indicates the degree or tier of political constituency or voting body at which a decision, representation, or electoral process is defined or applied.
-
B.
federalLevelElection
Indicates that the election takes place at the federal (national) level of government rather than at a state, regional, or local level.
-
C.
electionNumber
Indicates the specific ordinal or identifying number assigned to a particular election within a series or system of elections.
-
D.
electoralRank
Indicates the position or level an entity holds within an electoral hierarchy or ranking system.
-
E.
electoralBasis
Indicates the principle, rule, or criterion by which representatives or officials are chosen in an election.
- 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_69a88713ddc88190a969715658ebe7a8 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:37 p.m.