Triple
T13511153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ariana Dumbledore |
E321140
|
entity |
| Predicate | magicControl |
P110047
|
FINISHED |
| Object | uncontrolled |
—
|
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: uncontrolled | Statement: [Ariana Dumbledore, magicControl, uncontrolled]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magicControl Context triple: [Ariana Dumbledore, magicControl, uncontrolled]
-
A.
controlIntegration
Indicates that one entity manages or coordinates the incorporation and interaction of another entity within a larger system or process.
-
B.
controlsWith
Indicates that one entity exercises authority, direction, or regulatory power over another entity through specific means or mechanisms.
-
C.
controlLink
Indicates a relationship where one entity exerts control, influence, or governing authority over another entity or process.
-
D.
magicalObjectThatControls
Indicates a relationship where one magical object has the power to direct, influence, or command another entity or force.
-
E.
controlMedium
Indicates that an entity regulates, directs, or influences another entity through a particular medium or channel.
- F. None of above. chosen
Provenance (4 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_69d807629d6c8190998f1b9bb12d2ed0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaf86a6208190be8c18f7a0158f23 |
completed | April 12, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69dbae0b63748190b5e207f84b2532ea |
completed | April 12, 2026, 2:36 p.m. |
| PDg | Predicate description generation | batch_69dbaee128d88190b097be17fdd2f92b |
completed | April 12, 2026, 2:40 p.m. |
Created at: April 9, 2026, 9:43 p.m.