Triple
T23609971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Australian Idol |
E583009
|
entity |
| Predicate | winnerOfSeason2 |
P27408
|
FINISHED |
| Object | Casey Donovan |
—
|
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: Casey Donovan | Statement: [Australian Idol, winnerOfSeason2, Casey Donovan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerOfSeason2 Context triple: [Australian Idol, winnerOfSeason2, Casey Donovan]
-
A.
secondSeasonChampion
chosen
Indicates that the subject is the champion or winner of the second season of a competition, series, or event in relation to the object.
-
B.
secondSeasonChampionYear
Indicates the year in which an entity won a championship for the second season.
-
C.
secondRoundWinner
Indicates that the subject is the winner of the second round in a multi-round competition, contest, or process.
-
D.
secondEditionChampion
Indicates that an entity is the champion or winner of the second edition or iteration of a particular event, competition, or series.
-
E.
secondWinningSeason
Indicates that the season in question is the second time an entity (such as a team or individual) has achieved a winning record or successful outcome.
- 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_69e248faa2788190abb1581742daa6aa |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b0f399cc8190a18d94b60fdca042 |
completed | April 29, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:44 p.m.