Triple
T4570389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Griphook |
E123014
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Verne Troyer |
E240205
|
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: Verne Troyer | Statement: [Griphook, portrayedBy, Verne Troyer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Verne Troyer Context triple: [Griphook, portrayedBy, Verne Troyer]
-
A.
Verne Troyer
chosen
Verne Troyer was an American actor and stunt performer best known for his role as Mini-Me in the Austin Powers film series.
-
B.
Crispin Glover
Crispin Glover is an American actor, filmmaker, and author best known for his eccentric screen presence and memorable roles in films such as "Back to the Future" and "River's Edge."
-
C.
Matthew Lillard
Matthew Lillard is an American actor and director best known for his energetic, often comedic performances in films such as "Scream," "Scooby-Doo," and "Hackers."
-
D.
Victor Heerman
Victor Heerman was a British-born American screenwriter and film director best known for co-writing the Academy Award–winning adaptation of "Little Women" (1933).
-
E.
Lin Shaye
Lin Shaye is an American character actress best known for her prolific work in horror films, particularly the "Insidious" franchise, as well as numerous comedic roles.
- 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_69bd46466c7081909d07f36be2d08804 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd58c3eba48190af1fce6e1ca16943 |
completed | March 20, 2026, 2:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdd3c6806c81908fd374cd4537185e |
completed | March 20, 2026, 11:09 p.m. |
Created at: March 20, 2026, 1:10 p.m.