Triple
T14957396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drunk History |
E372966
|
entity |
| Predicate | hasHost |
P2592
|
FINISHED |
| Object | Derek Waters |
E1129276
|
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: Derek Waters | Statement: [Drunk History, hasHost, Derek Waters]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derek Waters Context triple: [Drunk History, hasHost, Derek Waters]
-
A.
Derek Waters
chosen
Derek Waters is an American actor, comedian, and writer best known for co-creating and hosting the Comedy Central series "Drunk History."
-
B.
Geoffrey Fletcher
Geoffrey Fletcher is an American screenwriter and filmmaker best known for his Academy Award–winning adapted screenplay for the film "Precious."
-
C.
Michael Cuesta
Michael Cuesta is an American film and television director and producer known for his work on series such as Homeland, Dexter, and Six Feet Under.
-
D.
Jeff Cronenweth
Jeff Cronenweth is an American cinematographer known for his stylish, atmospheric work on films such as "The Social Network" and collaborations with director David Fincher.
-
E.
Derek Dreyer
Derek Dreyer is a prominent computer scientist known for his work in programming languages, type theory, and formal verification.
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6cc73848190ac181782b20dc838 |
completed | April 15, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe8bda691481909c2d89a362782ed8 |
completed | May 9, 2026, 1:20 a.m. |
Created at: April 10, 2026, 2:40 a.m.