Triple
T37662464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Harming |
E937745
|
entity |
| Predicate | editionAvailableIn |
P44721
|
FINISHED |
| Object | Java Edition |
—
|
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: Java Edition | Statement: [Potion of Harming, editionAvailableIn, Java Edition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editionAvailableIn Context triple: [Potion of Harming, editionAvailableIn, Java Edition]
-
A.
hasEditionAvailability
Indicates that a particular edition of an item is available in a specified form, location, or channel.
-
B.
mayBeAvailableIn
Indicates that an entity has the potential to be obtainable, accessible, or present within a specified context, location, or medium.
-
C.
languageOfAvailableEditions
Indicates the language in which the available editions of a work or resource are published.
-
D.
hasEditionIn
chosen
Indicates that one entity has a specific edition or version that exists or is available in another entity (such as a particular format, language, or location).
-
E.
availableInCountry
Indicates that something can be legally or practically obtained, accessed, or used within a specified country.
- 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_69fbaa1321b48190af92a3e7ec24ec5b |
completed | May 6, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69fba8860f98819080b7bab05837b974 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.