Triple
T20119001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How High |
E490546
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Jamal King |
—
|
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: Jamal King | Statement: [How High, mainCharacter, Jamal King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jamal King Context triple: [How High, mainCharacter, Jamal King]
-
A.
Jamal King
chosen
Jamal King is a comedic stoner protagonist portrayed by Method Man in the 2001 film "How High."
-
B.
Anthony King
Anthony King is an American television writer, producer, and comedian known for his work on series such as The Afterparty and Broad City.
-
C.
Jamal Hill
Jamal Hill is an American film director known for his work in urban drama and independent cinema.
-
D.
Leamon King
Leamon King was an American sprinter and Olympic gold medalist known for his world-record performances in the 100 meters during the 1950s.
-
E.
Jamal Jones
Jamal Jones is a writer associated with the publication Glamorous, known for contributing written work to its content.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673c32bc8190a52875961fbcc5e2 |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:30 p.m.