Triple
T30619286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Tall T |
E779400
|
entity |
| Predicate | hasVillainCharacter |
P32100
|
FINISHED |
| Object | Frank Usher |
—
|
NE NERFINISHED |
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: Frank Usher | Statement: [The Tall T, hasVillainCharacter, Frank Usher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVillainCharacter Context triple: [The Tall T, hasVillainCharacter, Frank Usher]
-
A.
hasVillain
chosen
Indicates that one entity is the villain or primary antagonist associated with another entity.
-
B.
isTypeOfVillain
Indicates that one entity is classified as a particular type or category of villain in relation to another entity.
-
C.
featuresVillainActor
Indicates that the subject includes or presents an actor in the role of a villain.
-
D.
hasAntagonisticProtagonist
Indicates that the work features a main character who opposes or undermines the typical heroic or moral expectations of a traditional protagonist.
-
E.
fullyIntroducedAsAntagonistIn
Indicates that an entity is completely and explicitly presented in a work as an antagonist within the specified context or narrative.
- 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_69f224a3307081909a6dca8ca75dbf48 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: April 29, 2026, 8:26 p.m.