Triple
T7187618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fire Flower |
E167609
|
entity |
| Predicate | enablesAbility |
P67649
|
FINISHED |
| Object | throwing fireballs |
—
|
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: throwing fireballs | Statement: [Fire Flower, enablesAbility, throwing fireballs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enablesAbility Context triple: [Fire Flower, enablesAbility, throwing fireballs]
-
A.
grantsAbility
chosen
Indicates that one entity endows another entity with a specific capability or power that it did not previously possess.
-
B.
enablingPowerFor
Indicates that one entity provides the capability or authority that allows another entity to perform a specific function, action, or role.
-
C.
enablesService
Indicates that one entity provides the capability or necessary conditions for another entity to offer or perform a specific service.
-
D.
enabledBy
Indicates that one entity functions as the cause, condition, or resource that makes it possible for another entity’s action, state, or capability to occur or be realized.
-
E.
symbolicAbility
Indicates the capacity of an entity to understand, manipulate, or use symbols to represent concepts, objects, or relationships.
- 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_69c6888b5248819090499a884ee3ec39 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e8e2506881909fc4e81b9b79e873 |
completed | March 27, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69c6e752385c819096fbab55566ee2a8 |
completed | March 27, 2026, 8:23 p.m. |
Created at: March 27, 2026, 2:50 p.m.