Triple
T15619224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viktor Kudriavtsev |
E375502
|
entity |
| Predicate | notableStudent |
P4838
|
FINISHED |
| Object | Brian Joubert |
E1163339
|
NE 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: Brian Joubert | Statement: [Viktor Kudriavtsev, notableStudent, Brian Joubert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brian Joubert Context triple: [Viktor Kudriavtsev, notableStudent, Brian Joubert]
-
A.
Brian Joubert
chosen
Brian Joubert is a French former competitive figure skater best known for winning the 2007 World Championship and multiple European titles in men's singles.
-
B.
Eric Thibault
Eric Thibault is a professional basketball coach best known for leading the WNBA’s Washington Mystics.
-
C.
Joel Desrouleaux
Joel Desrouleaux is the brother of American singer, songwriter, and dancer Jason Derulo.
-
D.
Kevin Grevioux
Kevin Grevioux is an American actor, screenwriter, and comic book writer best known for co-creating the dark fantasy film franchise "Underworld."
-
E.
Michael Fessier
Michael Fessier was an American screenwriter and author known for his work on Hollywood films in the 1930s and 1940s, often contributing to romantic comedies and musicals.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85ccf2794819096cda4cbcb02d478 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e997ce481909b2f10d25705fbc6 |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f3b643c819093230df6cfe440b9 |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:13 a.m.