Triple
T20178406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avery Jones |
E492658
|
entity |
| Predicate | characterTypePerformed |
P49696
|
FINISHED |
| Object | evil ventriloquist dummy |
—
|
LITERAL 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: evil ventriloquist dummy | Statement: [Avery Jones, characterTypePerformed, evil ventriloquist dummy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterTypePerformed Context triple: [Avery Jones, characterTypePerformed, evil ventriloquist dummy]
-
A.
performedByCharacterType
Indicates that an action or event is carried out by a character belonging to a specified character type or category.
-
B.
typeOfCharacter
Indicates that one entity is a specific kind or category of character in relation to another entity.
-
C.
workCharacterType
chosen
Indicates that a work involves or features a character of a specified type or role.
-
D.
operatedByCharacter
Indicates that an operation, action, or process is carried out or controlled by a specific character.
-
E.
performedForCharacterPortrayedBy
Indicates that an action or performance was carried out for the benefit of a fictional character as portrayed by a specific actor.
- F. None of above.
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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668ed07c8819091bd9ffda237a91c |
completed | April 20, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69e55b0c11cc8190836d1eee5945f000 |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:36 p.m.