Triple
T37691925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Austrian legislative election 2019 |
E938827
|
entity |
| Predicate | greenPartyAbbreviation |
P84577
|
FINISHED |
| Object | Greens |
—
|
NE NERFINISHED |
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: Greens | Statement: [Austrian legislative election 2019, greenPartyAbbreviation, Greens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: greenPartyAbbreviation Context triple: [Austrian legislative election 2019, greenPartyAbbreviation, Greens]
-
A.
greenParty
Indicates that an entity is affiliated with, represents, or is associated with the Green Party in a political context.
-
B.
greenPartyFirstMP
Indicates that the person is the first Member of Parliament elected from the Green Party in a given political context or jurisdiction.
-
C.
greenPartyPopularVotePercentage
Indicates the proportion of total votes in an election that were cast for the Green Party, expressed as a percentage.
-
D.
seatsWonByGreenParty
Indicates the number of legislative or electoral seats that were won by the Green Party in a given election or governing body.
-
E.
politicalPartyAbbreviation
chosen
Indicates that a political party is known or referred to by a specific abbreviated form of its name.
- 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_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:18 p.m.