Triple
T9142978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1978 United States elections |
E219375
|
entity |
| Predicate | senateSeatsContestedApprox |
P11588
|
FINISHED |
| Object | one-third of United States Senate seats |
—
|
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: one-third of United States Senate seats | Statement: [1978 United States elections, senateSeatsContestedApprox, one-third of United States Senate seats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: senateSeatsContestedApprox Context triple: [1978 United States elections, senateSeatsContestedApprox, one-third of United States Senate seats]
-
A.
numberOfSeatsContested
chosen
Indicates the total count of seats in an election or contest that are being competed for or are up for selection.
-
B.
numberOfSenates
Indicates the total count of senate bodies associated with or present in a given context or entity.
-
C.
numberOfSeatsInSenate
Indicates the total count of seats allocated in a given senate.
-
D.
numberOfSenateDistricts
Indicates the total count of senate districts associated with a given entity or jurisdiction.
-
E.
contestsSeatsIn
Indicates that an individual or party is competing for elected positions within a specified electoral district or governing body.
- 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_69ca83e121dc81909912bd66953081c5 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8f5f740819098236ada5b95889d |
completed | April 1, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69cc6603ce8c8190bf6e8d6754bdec54 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:19 p.m.