Triple
T10026762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mavis Dracula |
E200748
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Todd Durham |
E392934
|
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: Todd Durham | Statement: [Mavis Dracula, creator, Todd Durham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Todd Durham Context triple: [Mavis Dracula, creator, Todd Durham]
-
A.
Todd Durham
chosen
Todd Durham is an American screenwriter and filmmaker best known for creating the "Hotel Transylvania" animated film franchise.
-
B.
Darryl Philbin
Darryl Philbin is a laid-back yet sharp-witted warehouse foreman who becomes a key supporting character and later office employee in the U.S. version of The Office.
-
C.
Bill Nunn
Bill Nunn was an American character actor best known for his memorable supporting roles in films like "Do the Right Thing" and the "Spider-Man" trilogy.
-
D.
Doug Bowne
Doug Bowne is a musician best known for his work with the new wave band Tom Tom Club.
-
E.
Mark O’Keefe
Mark O’Keefe is an American screenwriter best known for writing comedy films such as "Bruce Almighty" and "Click."
- 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_69ca831c45f08190ac1505cc15076608 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcde3c1b88190924e6158f406b453 |
completed | April 2, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26ac9cdfc8190b91746855bf3de12 |
completed | April 5, 2026, 1:59 p.m. |
Created at: March 30, 2026, 8:54 p.m.