Triple
T27900055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dancing with the Stars (season 23) |
E705605
|
entity |
| Predicate | featuresCelebrityContestant |
P170066
|
FINISHED |
| Object | Laurie Hernandez |
—
|
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: Laurie Hernandez | Statement: [Dancing with the Stars (season 23), featuresCelebrityContestant, Laurie Hernandez]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCelebrityContestant Context triple: [Dancing with the Stars (season 23), featuresCelebrityContestant, Laurie Hernandez]
-
A.
featuresContestantsFrom
Indicates that something, typically a show or event, includes contestants originating from a specified source or group.
-
B.
featuresContestants
Indicates that something (such as an event, show, or competition) includes or presents certain individuals as contestants.
-
C.
featuresContestantSelectionBy
Indicates that something includes or presents a contestant selection process carried out by a specified agent or entity.
-
D.
celebrityParticipant
chosen
Indicates that an entity takes part in an event, activity, or production specifically in the role of a celebrity.
-
E.
contestantFullName
Indicates that the relationship specifies the complete, properly ordered name of a contestant.
- 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_69ef96b490ac8190a412d04c5d009f3e |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fdbc5ef46c8190bbcfb9798f4615b7 |
completed | May 8, 2026, 10:35 a.m. |
| PD | Predicate disambiguation | batch_69fdbb270338819082ce3f73903e884f |
completed | May 8, 2026, 10:29 a.m. |
Created at: April 27, 2026, 6:41 p.m.