Triple
T20723920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scorpius Malfoy |
E509385
|
entity |
| Predicate | patronusStatus |
P62712
|
FINISHED |
| Object | no known Patronus in canon |
—
|
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: no known Patronus in canon | Statement: [Scorpius Malfoy, patronusStatus, no known Patronus in canon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patronusStatus Context triple: [Scorpius Malfoy, patronusStatus, no known Patronus in canon]
-
A.
patronus
Indicates that one entity serves as a protective guardian or spiritual defender for another entity.
-
B.
patronusAbility
chosen
Indicates the ability of an entity to produce or use a Patronus (a protective magical manifestation) in relation to another entity or context.
-
C.
patronState
Indicates a relationship where one state acts as a protector, sponsor, or dominant supporter of another state or political entity.
-
D.
patronusFormType
Indicates the specific animal or shape that a Patronus takes when conjured.
-
E.
hasPatronCharacter
Indicates that one entity serves as a patron, protector, or guiding figure for another entity.
- 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_69e0b4c4cc648190b45fda6e2b20af56 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1e662f08190917ee043612d413e |
completed | April 21, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69e5c04b31248190b9b9d91b5cb854e3 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:28 p.m.