Triple
T7729769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bronisław Komorowski |
E175219
|
entity |
| Predicate | electionLostTo |
P354
|
FINISHED |
| Object | Andrzej Duda in 2015 Polish presidential election |
—
|
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: Andrzej Duda in 2015 Polish presidential election | Statement: [Bronisław Komorowski, electionLostTo, Andrzej Duda in 2015 Polish presidential election]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electionLostTo Context triple: [Bronisław Komorowski, electionLostTo, Andrzej Duda in 2015 Polish presidential election]
-
A.
popularVoteLoser
Indicates that the subject became the winner of an election despite receiving fewer popular votes than at least one opponent.
-
B.
defeatedCandidate
chosen
Indicates that one candidate has won an election or contest against another candidate, causing the other to lose.
-
C.
popularVoteLoserParty
Indicates that the subject is the political party of a candidate who lost the popular vote in an election.
-
D.
lostPresidency
Indicates that an entity who previously held a presidency position has ceased to hold that office, typically as a result of an election or other loss of power.
-
E.
electoralSuccess
Indicates that an entity has achieved a favorable or winning outcome in an election or electoral process.
- 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_69c6995e912c81909a49a2657103f786 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:06 p.m.