Triple
T11766591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1996 Russian presidential election |
E279796
|
entity |
| Predicate | turnoutSecondRound |
P29796
|
FINISHED |
| Object | 68.8% |
—
|
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: 68.8% | Statement: [1996 Russian presidential election, turnoutSecondRound, 68.8%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: turnoutSecondRound Context triple: [1996 Russian presidential election, turnoutSecondRound, 68.8%]
-
A.
turnout
chosen
Indicates the number or proportion of participants who attend or take part in an event or activity.
-
B.
secondRoundCandidate
Indicates that an entity has advanced past an initial selection stage and is being considered as a candidate in a second round of evaluation or decision-making.
-
C.
secondPartyPopularVoteShare
Indicates the proportion of total popular votes received by the second party in an election.
-
D.
includesSecondRound
Indicates that the referenced process, event, or activity contains or involves a second round or phase as part of its structure.
-
E.
secondRoundRunnerUpVoteSharePercentage
Indicates the percentage of total votes received by the candidate who finished as runner-up in the second round of a contest or 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a8c2e8b08190a31b1e284fca2aee |
completed | April 10, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69d8a242cd8c819086ed6c5f292dc8cb |
completed | April 10, 2026, 7:09 a.m. |
Created at: April 8, 2026, 9:41 p.m.