Triple
T37662583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Water Breathing |
E937748
|
entity |
| Predicate | convertedToSplashBy |
P23777
|
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 Water Breathing, convertedToSplashBy, Gunpowder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convertedToSplashBy Context triple: [Potion of Water Breathing, convertedToSplashBy, Gunpowder]
-
A.
convertedBy
chosen
Indicates that one entity has been transformed or changed in form, state, or representation through the action or process performed by another entity.
-
B.
convertedIn
Indicates that one entity has been transformed, changed, or translated into another form, state, or representation within a specified context.
-
C.
hasConvertedTo
Indicates that an entity has changed its previous state, status, form, or affiliation into a new one.
-
D.
someConvertedTo
Indicates that a portion of one entity has been transformed or changed into another entity.
-
E.
convertedFrom
Indicates that one entity has been transformed or changed in form, type, or representation from another entity.
- 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_69fcd867f36081908c88c55a6a1404c1 |
completed | May 7, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f47b188190b4cf4b4c748d9d03 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:18 p.m.