Triple
T37455815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alchemist (Torchlight) |
E930795
|
entity |
| Predicate | canRespec |
P160358
|
FINISHED |
| Object | limited skill points |
—
|
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: limited skill points | Statement: [Alchemist (Torchlight), canRespec, limited skill points]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canRespec Context triple: [Alchemist (Torchlight), canRespec, limited skill points]
-
A.
canRevertTo
Indicates that one state, version, or condition has the ability to be changed back or restored to another prior state, version, or condition.
-
B.
isReforgingOf
Indicates that one object is the result of being remade, reshaped, or reconstructed from another pre-existing object.
-
C.
mainCharacterSpecialization
Indicates the specific role, class, or area of expertise that the main character is focused on or specialized in.
-
D.
canReinstate
Indicates that one entity has the authority or ability to restore another entity or state to a previous valid or active condition.
-
E.
canChangeIn
chosen
Indicates that one entity is capable of undergoing alteration, transformation, or variation within the context or influence of another entity or condition.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb92efc5948190a040ba2028bab964 |
completed | May 6, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0b52588190bb29937a43b99b5e |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:17 p.m.