Triple
T14348779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Discovery of Witches |
E355796
|
entity |
| Predicate | featuresSupernaturalSpecies |
P7733
|
FINISHED |
| Object | witches |
—
|
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: witches | Statement: [A Discovery of Witches, featuresSupernaturalSpecies, witches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresSupernaturalSpecies Context triple: [A Discovery of Witches, featuresSupernaturalSpecies, witches]
-
A.
mainSupernaturalEntity
Indicates that one entity is the primary or central supernatural being associated with, influencing, or defining another entity or context.
-
B.
featuresSpecies
chosen
Indicates that something includes, presents, or highlights a particular species as part of its content or composition.
-
C.
featuresMonster
Indicates that something includes or prominently presents a monster as part of its content or composition.
-
D.
containsSupernaturalElement
Indicates that the subject involves or features a supernatural, magical, or otherworldly element beyond normal natural laws.
-
E.
fictionalSpecies
Indicates that the subject is a species that exists only in fiction or imaginary works, rather than in real life.
- 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8e8d081c8190ac805726a3e98f4c |
completed | April 14, 2026, 6:59 p.m. |
| PD | Predicate disambiguation | batch_69de2a9958e881909d03ac03f135163e |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:14 a.m.