Triple
T22571837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oliver Kahn |
E558092
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | King Kahn |
—
|
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: King Kahn | Statement: [Oliver Kahn, nickname, King Kahn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: King Kahn Context triple: [Oliver Kahn, nickname, King Kahn]
-
A.
King Kahn
chosen
King Kahn is the famous nickname of Oliver Kahn, the legendary German goalkeeper renowned for his commanding presence, leadership, and intense competitive spirit.
-
B.
Kral
Kral is a surname most notably associated with Australian film and television composer Robert J. Kral.
-
C.
King Khan
King Khan is the popular honorific nickname of Indian film superstar Shah Rukh Khan, reflecting his status as one of Bollywood’s most successful and influential actors.
-
D.
Krall
Krall is the main antagonist in the film "Star Trek Beyond," a former Starfleet officer transformed into a vengeful alien warlord who seeks to destroy the Federation.
-
E.
King Wizard
"King Wizard" is a song by Kid Cudi from his 2013 studio album *Indicud*, showcasing his signature blend of introspective lyrics and atmospheric hip-hop production.
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fae1ed881909430769a0015c39c |
completed | April 29, 2026, 1:32 a.m. |
Created at: April 16, 2026, 8:52 p.m.