Triple
T28638898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Percival Graves |
E724865
|
entity |
| Predicate | magicSchoolAttended |
P23183
|
FINISHED |
| Object | Ilvermorny School of Witchcraft and Wizardry |
—
|
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: Ilvermorny School of Witchcraft and Wizardry | Statement: [Percival Graves, magicSchoolAttended, Ilvermorny School of Witchcraft and Wizardry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magicSchoolAttended Context triple: [Percival Graves, magicSchoolAttended, Ilvermorny School of Witchcraft and Wizardry]
-
A.
schoolAttended
chosen
Indicates that one entity has attended, or been enrolled as a student at, the school represented by the other entity.
-
B.
schoolOf
Indicates that an educational institution is the one where a person studied, worked, or is otherwise academically affiliated.
-
C.
schoolTypeAttended
Indicates the specific type or category of school that an entity has attended.
-
D.
educationLocation
Indicates the place or institution where an entity received education or underwent formal learning.
-
E.
educationalInstitutionServed
Indicates that one entity provides services, support, or resources to a particular educational institution.
- 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_69f01d8328c48190bc0e5f9b9b848582 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a84f848190b5898ee7566fb84e |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:42 a.m.