Triple
T12183797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crash Course |
E290282
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Hank Green |
E919907
|
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: Hank Green | Statement: [Crash Course, creator, Hank Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hank Green Context triple: [Crash Course, creator, Hank Green]
-
A.
Hank Green
chosen
Hank Green is an American science communicator, author, and entrepreneur best known for co-founding the educational YouTube channels Crash Course and SciShow.
-
B.
Scott Aukerman
Scott Aukerman is an American comedian, writer, and podcast host best known as the creator and host of the comedy podcast and TV series "Comedy Bang! Bang!"
-
C.
Carl Wheezer
Carl Wheezer is a timid, allergy-prone boy and one of Jimmy Neutron’s best friends in the animated series "The Adventures of Jimmy Neutron: Boy Genius."
-
D.
Alex Shulman
Alex Shulman is a person notable enough to be recognized as a bearer of the surname Shulman, though specific widely known biographical details are not clearly established.
-
E.
Jason Gedrick
Jason Gedrick is an American actor best known for his breakout role in 1980s action films and later work in television dramas such as "Murder One" and "Boomtown."
- 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_69d6ab64de5881908d56eb7a75c6cc69 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d915fd8dac8190928059ad2b6bbbf3 |
completed | April 10, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f6aecb0881909084f3ff2a9e52ea |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:50 p.m.