Triple
T33818502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eurovision Song Contest 1990 |
E866758
|
entity |
| Predicate | previousWinningPerformer |
P60796
|
FINISHED |
| Object | Riva |
—
|
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: Riva | Statement: [Eurovision Song Contest 1990, previousWinningPerformer, Riva]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousWinningPerformer Context triple: [Eurovision Song Contest 1990, previousWinningPerformer, Riva]
-
A.
winningPerformer
Indicates that the referenced performer is the one who achieved victory or first place in a particular competition, event, or contest.
-
B.
winnerArtist
Indicates that an artist is the winner of a particular contest, award, or competitive event.
-
C.
lastWinner
chosen
Indicates that one entity is the most recent winner in a sequence of competitions, contests, or events involving the other entity.
-
D.
winnerPreviouslyWon
Indicates that the winner has won the same or a related contest/event at least once before.
-
E.
finalPerformer
Indicates that an entity is the last or concluding performer in a sequence of performances or performers.
- 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_69f349911a8c81908478662194b23d8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff1ba8694481909ceb36f26ca85612 |
completed | May 9, 2026, 11:34 a.m. |
| PD | Predicate disambiguation | batch_69ff1b27f0f08190a9e74308c5b3d1ba |
completed | May 9, 2026, 11:31 a.m. |
Created at: May 1, 2026, 1:46 a.m.