Triple
T37662539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Weakness |
E937747
|
entity |
| Predicate | canBeMadeSplashWith |
P5771
|
FINISHED |
| Object | gunpowder |
—
|
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: gunpowder | Statement: [Potion of Weakness, canBeMadeSplashWith, gunpowder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeMadeSplashWith Context triple: [Potion of Weakness, canBeMadeSplashWith, gunpowder]
-
A.
hasSplashEffect
Indicates that one entity produces or is associated with a splash-like visual or physical effect on another entity or in its environment.
-
B.
canMake
chosen
Indicates that one entity has the ability or capacity to create, produce, or assemble another entity.
-
C.
hasSplashdown
Indicates that an object or vehicle returns from flight or space and lands in water rather than on solid ground.
-
D.
canBeFiredIn
Indicates that an entity (such as a weapon or device) is capable of being discharged or operated within a specified medium, environment, or container.
-
E.
splashLevel
Indicates the degree or intensity to which something causes or experiences splashing.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff59b33a38819086cc9aa19b81748b |
completed | May 9, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69ff587758f88190a39c2164341dc554 |
completed | May 9, 2026, 3:53 p.m. |
Created at: May 3, 2026, 4:18 p.m.