Triple
T26519188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Pevensie |
E669904
|
entity |
| Predicate | magicalObjectFunction |
P160683
|
FINISHED |
| Object | summons help when blown |
—
|
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: summons help when blown | Statement: [Susan Pevensie, magicalObjectFunction, summons help when blown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magicalObjectFunction Context triple: [Susan Pevensie, magicalObjectFunction, summons help when blown]
-
A.
magicalObject
Indicates that one entity is a magical object associated with, used by, or affecting another entity.
-
B.
functionInMagic
chosen
Indicates that an entity serves a specific role or performs a particular function within a magical system, process, or context.
-
C.
magicalObjectThatControls
Indicates a relationship where one magical object has the power to direct, influence, or command another entity or force.
-
D.
usesMagicFor
Indicates that one entity employs or applies magic as a means to achieve, affect, or perform something involving another entity or context.
-
E.
magicField
Indicates the presence or influence of a magical force or energy affecting an entity or area.
- 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_69eeb31b6dcc8190b30632dc3928a0c0 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f613c06530819095609b53dda121b4 |
completed | May 2, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69f60b89cc048190a9feb24466006be0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 1:26 a.m.