Triple
T36054505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Potter's wand |
E1042905
|
entity |
| Predicate | usedForMagicType |
P49967
|
FINISHED |
| Object | defensive magic |
—
|
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: defensive magic | Statement: [Harry Potter's wand, usedForMagicType, defensive magic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedForMagicType Context triple: [Harry Potter's wand, usedForMagicType, defensive magic]
-
A.
usesMagicFor
Indicates that one entity employs or applies magic as a means to achieve, affect, or perform something involving another entity or context.
-
B.
associatedWithMagicType
chosen
Indicates a relationship where something is linked or connected to a particular type or category of magic.
-
C.
usesMagic
Indicates that an entity performs actions or achieves effects by employing magical powers or supernatural abilities.
-
D.
usedForSpell
Indicates that something serves as a component, tool, or resource employed in performing or casting a spell.
-
E.
usedInType
Indicates that something serves as a component, element, or example within a particular type or category.
- 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_69f76e2f09448190b0486d5ecad5e243 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd4129a8848190a5002150278ac689 |
completed | May 8, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69fd3e0515ec8190937c7af71ebc3875 |
completed | May 8, 2026, 1:36 a.m. |
Created at: May 3, 2026, 4:08 p.m.