Triple
T37662449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Harming |
E937745
|
entity |
| Predicate | hasLevelVariant |
P455
|
FINISHED |
| Object | Potion of Harming I |
—
|
NE NERFINISHED |
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: Potion of Harming I | Statement: [Potion of Harming, hasLevelVariant, Potion of Harming I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLevelVariant Context triple: [Potion of Harming, hasLevelVariant, Potion of Harming I]
-
A.
hasVariant
chosen
Indicates that one entity exists as an alternative form, version, or variation of another entity.
-
B.
hasLevelType
Indicates that an entity is associated with a specific type or category of level (e.g., difficulty, hierarchy, or stage).
-
C.
hasVariantSystem
Indicates that one system is an alternative or variant form of another system within the same general framework or category.
-
D.
hasVariantsIn
Indicates that an entity exists in multiple alternative forms or versions within a specified context or set.
-
E.
hasLevel
Indicates that an entity possesses or is associated with a particular degree, rank, or stage within an ordered scale or hierarchy.
- 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_69fe920a437081908d5174e8cf7a53a6 |
completed | May 9, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69fe919a9a6c8190acb4483f386e6db7 |
completed | May 9, 2026, 1:44 a.m. |
Created at: May 3, 2026, 4:18 p.m.