Triple
T12913246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mortal Folly |
E308911
|
entity |
| Predicate | featuresVillainType |
P32101
|
FINISHED |
| Object | undead sorcerer |
—
|
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: undead sorcerer | Statement: [Mortal Folly, featuresVillainType, undead sorcerer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresVillainType Context triple: [Mortal Folly, featuresVillainType, undead sorcerer]
-
A.
featuresVillainActor
Indicates that the subject includes or presents an actor in the role of a villain.
-
B.
villainDescription
chosen
Indicates that one entity provides a description or characterization of a villainous role or antagonist associated with another entity.
-
C.
facesAntagonistType
Indicates that an entity confronts or opposes an antagonist of a specified type.
-
D.
hasVillain
Indicates that one entity is the villain or primary antagonist associated with another entity.
-
E.
featuresCharacterWith
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9719f96248190b746f9d4a468560c |
completed | April 10, 2026, 9:54 p.m. |
| PD | Predicate disambiguation | batch_69d96fa9b7708190a9e9fa30f59ff580 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:41 p.m.