Triple
T17858950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kym Johnson |
E446014
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Kym Johnson |
—
|
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: Kym Johnson | Statement: [Kym Johnson, name, Kym Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kym Johnson Context triple: [Kym Johnson, name, Kym Johnson]
-
A.
Kym Johnson
chosen
Kym Johnson is an Australian professional ballroom dancer and choreographer best known for her long-running role as a pro on the U.S. television show "Dancing with the Stars."
-
B.
Kimberly Drummond
Kimberly Drummond is a central character on the American sitcom "Diff'rent Strokes," known as the teenage daughter in the wealthy Drummond family who helps bridge the cultural gap with her adopted brothers.
-
C.
Kym Lucas
Kym Lucas is an American Episcopal bishop who serves as the diocesan leader of the Episcopal Diocese of Colorado.
-
D.
Jennifer Johnson
Jennifer Johnson is known as the mother of Quake, a character associated with this relationship.
-
E.
Tanya Jones
Tanya Jones is best known as the wife of British actor and former footballer Vinnie Jones.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4978e68ec8190a4306f7b7bb058d7 |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.