Triple
T14081182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Extreme Behavior |
E338871
|
entity |
| Predicate | performer |
P1363
|
FINISHED |
| Object | Mark King |
E338869
|
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: Mark King | Statement: [Extreme Behavior, performer, Mark King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark King Context triple: [Extreme Behavior, performer, Mark King]
-
A.
Mark King
chosen
Mark King is a musician best known as the lead vocalist and bassist of the British jazz-funk band Level 42.
-
B.
Mark King
Mark King is an actor known for appearing in the film "Caveman."
-
C.
David King
David King is the named lead plaintiff in the landmark U.S. Supreme Court case King v. Burwell, which challenged federal health insurance subsidies under the Affordable Care Act.
-
D.
David King
David King is a graphic designer best known for creating the cover art for the Jimi Hendrix Experience album "Axis: Bold as Love."
-
E.
Jonathan King
Jonathan King is a film producer best known for his work on the biographical legal drama "On the Basis of Sex," which chronicles Ruth Bader Ginsburg's early career.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd27ff5b7081908ab27d5851b274ea |
completed | May 8, 2026, 12:02 a.m. |
Created at: April 9, 2026, 10:21 p.m.