Triple
T37457067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secret Mage |
E930825
|
entity |
| Predicate | burnTool |
P5659
|
FINISHED |
| Object | Fireball |
—
|
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: Fireball | Statement: [Secret Mage, burnTool, Fireball]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: burnTool Context triple: [Secret Mage, burnTool, Fireball]
-
A.
burnMode
Indicates that one entity is operating in or causing a state of intense, high-output, or destructive activity in another entity or process.
-
B.
burnCapability
Indicates that an entity has the ability or potential to burn, ignite, or cause combustion under certain conditions.
-
C.
attackToolExample
chosen
Indicates that a specific tool or method is used as an example of how an attack is or can be carried out.
-
D.
burnProfile
Indicates that one entity records or defines how another entity burns, such as its combustion characteristics or burn behavior.
-
E.
burnsWhen
Indicates that one entity causes another entity to ignite or combust when they come into contact or under specified conditions.
- 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.