Triple
T38061183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Assassin (Diablo II) |
E950343
|
entity |
| Predicate | canSetTrap |
P32024
|
FINISHED |
| Object | Wake of Fire |
—
|
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: Wake of Fire | Statement: [Assassin (Diablo II), canSetTrap, Wake of Fire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canSetTrap Context triple: [Assassin (Diablo II), canSetTrap, Wake of Fire]
-
A.
canSet
Indicates that one entity has the ability or permission to assign, configure, or change a property, value, or state of another entity.
-
B.
hasTrapType
chosen
Indicates that an entity is associated with, or characterized by, a specific type or category of trap.
-
C.
canEnable
Indicates that one entity has the capability or authority to activate, turn on, or make another entity or function operational.
-
D.
canBeMonitoredWith
Indicates that one entity is suitable or able to be observed, tracked, or supervised using another specified entity or method.
-
E.
canConstrain
Indicates that one entity has the ability or authority to limit, restrict, or impose conditions on another entity or its behavior.
- 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_69f76f01e63c819093b6012fc974f35a |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc44c7e73c819082d4fc1900fb9632 |
completed | May 7, 2026, 7:52 a.m. |
| PD | Predicate disambiguation | batch_69fbc8efffbc8190a139798ad1880526 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:21 p.m.