Triple
T7452282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 FIFA World Cup |
E172035
|
entity |
| Predicate | mascot |
P52
|
FINISHED |
| Object | Zabivaka |
E290487
|
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: Zabivaka | Statement: [2018 FIFA World Cup, mascot, Zabivaka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zabivaka Context triple: [2018 FIFA World Cup, mascot, Zabivaka]
-
A.
Zabivaka
chosen
Zabivaka is the wolf character that served as the official mascot for major international football tournaments hosted by Russia, including the 2018 FIFA World Cup.
-
B.
Xombi
Xombi is a Milestone Media comic book series that follows an immortal, nanotechnology-enhanced man battling supernatural and horror-themed threats.
-
C.
Groza
Groza is a surname most notably associated with Lou Groza, a Hall of Fame American football placekicker and offensive tackle for the Cleveland Browns.
-
D.
MabThera
MabThera is Roche’s brand name for rituximab, a monoclonal antibody used primarily to treat certain types of blood cancers and autoimmune diseases.
-
E.
Reaper
Reaper is a comedic supernatural television series about a young man who becomes a bounty hunter for the Devil, capturing escaped souls from Hell.
- 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_69c68a66554c8190add75c65942c0317 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f38d6a8c8190af2e73c719da87a6 |
completed | March 27, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c827b9a6048190bd3e3594b9cff2b7 |
completed | March 28, 2026, 7:10 p.m. |
Created at: March 27, 2026, 3:14 p.m.