Triple
T35686234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dancing with the Stars (US) season 17 |
E1031155
|
entity |
| Predicate | celebrityContestant |
P46216
|
FINISHED |
| Object | Amber Riley |
—
|
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: Amber Riley | Statement: [Dancing with the Stars (US) season 17, celebrityContestant, Amber Riley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: celebrityContestant Context triple: [Dancing with the Stars (US) season 17, celebrityContestant, Amber Riley]
-
A.
celebrityParticipant
Indicates that an entity takes part in an event, activity, or production specifically in the role of a celebrity.
-
B.
contestantOn
chosen
Indicates that one entity participates as a competitor in a contest, show, or competition associated with another entity.
-
C.
celebrityMatch
Indicates a relationship where one entity is identified as a suitable or corresponding celebrity counterpart or pairing for another entity.
-
D.
inauguralFinalist
Indicates that an entity was a finalist in the inaugural (first-ever) instance of a competition, award, or event.
-
E.
celebratedEntity
Indicates that one entity is honored, praised, or recognized in a special way by another entity or within a particular context.
- 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_69f76e0bb6608190ad3a1880be54a17d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a01fadac8190a429777cec614eca |
completed | May 3, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69f79e4d885881908a3612e2e75cf84f |
completed | May 3, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:05 p.m.