Triple
T37691922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Austrian legislative election 2019 |
E938827
|
entity |
| Predicate | thirdLargestPartyVoteShare |
P101671
|
FINISHED |
| Object | 16.2% |
—
|
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: 16.2% | Statement: [Austrian legislative election 2019, thirdLargestPartyVoteShare, 16.2%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdLargestPartyVoteShare Context triple: [Austrian legislative election 2019, thirdLargestPartyVoteShare, 16.2%]
-
A.
thirdLargestPartySeats
Indicates the number of seats held by the third-largest political party in a given legislative body or election outcome.
-
B.
thirdLargestPartyBySeats
Indicates that the subject is the political party holding the third-highest number of seats in a specified legislative body or election context.
-
C.
thirdPlaceVoteShare
chosen
Indicates the proportion of total votes received by the candidate or option that finished in third place in an election or contest.
-
D.
sixthLargestPartyVoteSharePercentage
Indicates the percentage of total votes received by the sixth-largest political party in an election.
-
E.
thirdPlaceParty
Indicates that an entity finished in third place in a competitive event or ranking.
- 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_69f76eda6ae48190b3111071eeacc038 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd57ba740c8190bd1d40166fccccb7 |
completed | May 8, 2026, 3:25 a.m. |
| PD | Predicate disambiguation | batch_69fd55ee82b881908a639da3a41b3af6 |
completed | May 8, 2026, 3:18 a.m. |
Created at: May 3, 2026, 4:18 p.m.