Triple
T30480807
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyoko Ina |
E775578
|
entity |
| Predicate | wonTitleWithPartner |
P29747
|
FINISHED |
| Object | U.S. pairs champion with Jason Dungjen |
—
|
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: U.S. pairs champion with Jason Dungjen | Statement: [Kyoko Ina, wonTitleWithPartner, U.S. pairs champion with Jason Dungjen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonTitleWithPartner Context triple: [Kyoko Ina, wonTitleWithPartner, U.S. pairs champion with Jason Dungjen]
-
A.
wonTitleWith
chosen
Indicates that an entity secured a specific title, award, or championship while being associated with or representing another entity (such as a team, organization, or group).
-
B.
wonTitleFrom
Indicates that one entity obtained a title or championship by defeating or surpassing another specific entity who previously held it.
-
C.
winnerCreditedAs
Indicates the name or designation under which the winner is officially recorded or credited for a particular award, contest, or achievement.
-
D.
doubleWinner
Indicates that the same entity has won the relevant award, contest, or recognition twice.
-
E.
winnerProfessionalPartner
Indicates that one entity is the professional partner of the winning participant in a competition or contest.
- 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_69f22497341481909c21ba329fadaa6b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f687415610819081818d08f7c79a81 |
completed | May 2, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69f678d2196c8190b9d0d2fcd47cc539 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:12 p.m.