Triple
T23560525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jerry Nelson |
E579223
|
entity |
| Predicate | performedCharacter |
P47022
|
FINISHED |
| Object | Crazy Harry |
—
|
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: Crazy Harry | Statement: [Jerry Nelson, performedCharacter, Crazy Harry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crazy Harry Context triple: [Jerry Nelson, performedCharacter, Crazy Harry]
-
A.
Crazy Harry
chosen
Crazy Harry is a wild-eyed Muppet character best known for his maniacal love of explosions and chaotic pranks.
-
B.
Handsome Harry
Handsome Harry is a 2009 independent crime drama film that follows a former sailor confronting his past involvement in a brutal assault as he reconnects with old Navy buddies.
-
C.
Hurry Harry March
Hurry Harry March is a character connected to Judith Hutter in James Fenimore Cooper’s Leatherstocking Tales, contributing to the frontier drama and interpersonal conflicts of the series.
-
D.
Happy Harry Hard-on
Happy Harry Hard-on is the rebellious on-air persona of the teenage pirate radio DJ in the film "Pump Up the Volume," used to anonymously broadcast provocative and subversive commentary.
-
E.
Hap-Hazard
Hap-Hazard is a notable work by American journalist and lecturer Kate Field, reflecting her wit and social commentary.
- 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_69e245fe24588190888f3aec8407d8e3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1af680ee88190a23a6f9fed7ae757 |
completed | April 29, 2026, 7:12 a.m. |
Created at: April 17, 2026, 6:15 p.m.