Triple
T33608645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1988 United States Senate elections |
E860925
|
entity |
| Predicate | percentageParty2 |
P166215
|
FINISHED |
| Object | 49.0% |
—
|
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: 49.0% | Statement: [1988 United States Senate elections, percentageParty2, 49.0%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageParty2 Context triple: [1988 United States Senate elections, percentageParty2, 49.0%]
-
A.
percentageParty1
Indicates the proportion or share attributed to the first party in a relationship, typically expressed as a percentage of some total.
-
B.
oppositionPercentage
Indicates the proportion of entities or participants that are in opposition to a given proposal, action, or subject relative to the whole.
-
C.
partyNumber
Indicates the identifier or ordinal position assigned to a specific party within a multi-party relationship or transaction.
-
D.
rulingPartyPopularVotePercentage
Indicates the percentage of the total popular vote received by the party currently in power or holding the ruling position.
-
E.
opponentPopularVotePercentage
chosen
Indicates the percentage of the total popular vote received by the opposing candidate or party 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_69f3498037c88190a4500f002b5540e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f71362f1448190985a80ce7af475cb |
completed | May 3, 2026, 9:20 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:41 a.m.