Triple
T25557076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jennifer Brady |
E640600
|
entity |
| Predicate | defeatedInFinalBy |
P68187
|
FINISHED |
| Object | Naomi Osaka |
—
|
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: Naomi Osaka | Statement: [Jennifer Brady, defeatedInFinalBy, Naomi Osaka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defeatedInFinalBy Context triple: [Jennifer Brady, defeatedInFinalBy, Naomi Osaka]
-
A.
defeatedBy
Indicates that one entity has been beaten, overcome, or conquered by another in a contest, conflict, or competition.
-
B.
finalBoutLoser
chosen
Indicates that an entity is the competitor who lost in the final bout of a match, tournament, or competition.
-
C.
finalOpponentOf
Indicates that one entity serves as the last or ultimate opponent faced by another entity in a sequence of confrontations or competitions.
-
D.
undefeatedTeamInFinal
Indicates that a team reached the final match of a competition and did so without having lost any game up to and including that final.
-
E.
finalsLosingTeam
Indicates the team that was defeated in the final match of a competition or tournament.
- 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_69e75dc101a881909fd33b02174e9768 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8cb186c819099b247e4a8cbd367 |
completed | May 2, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 3:40 p.m.