Triple
T37662732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Fire Resistance |
E937751
|
entity |
| Predicate | hasSplashVariant |
P455
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Potion of Fire Resistance, hasSplashVariant, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSplashVariant Context triple: [Potion of Fire Resistance, hasSplashVariant, true]
-
A.
hasSplashdown
Indicates that an object or vehicle returns from flight or space and lands in water rather than on solid ground.
-
B.
hasVariant
chosen
Indicates that one entity exists as an alternative form, version, or variation of another entity.
-
C.
hasDistributionVariant
Indicates that one entity is a variant or alternative form of another entity specifically in terms of its distribution characteristics or pattern.
-
D.
hasVariantSystem
Indicates that one system is an alternative or variant form of another system within the same general framework or category.
-
E.
hasImmersiveVersionOf
Indicates that one entity is an immersive (e.g., VR/AR or fully enveloping) version or presentation of 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_69feff70fbec8190b1ff5f943f29613e |
completed | May 9, 2026, 9:33 a.m. |
| PD | Predicate disambiguation | batch_69fefbcd5b7881909cfe52b32f8a4301 |
completed | May 9, 2026, 9:18 a.m. |
Created at: May 3, 2026, 4:18 p.m.