Triple
T14641814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sokka |
E343741
|
entity |
| Predicate | bendingAbility |
P8715
|
FINISHED |
| Object | non-bender |
—
|
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: non-bender | Statement: [Sokka, bendingAbility, non-bender]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bendingAbility Context triple: [Sokka, bendingAbility, non-bender]
-
A.
bendAngle
Indicates the degree to which one part is bent relative to another, typically measured as the angle formed at their joint or intersection.
-
B.
flexibility
Indicates the degree to which an entity can adapt, bend, or change its behavior, structure, or response in relation to other entities or conditions.
-
C.
positionFlexibility
Indicates the degree to which an entity’s role, location, or alignment can change or be adjusted relative to others or to a reference point.
-
D.
forceAbility
Indicates that one entity has the power or capacity to compel, influence, or cause another entity to act or change in a particular way.
-
E.
ability
chosen
Indicates that an entity has the capacity or power to perform a particular action or achieve a specific outcome.
- 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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4e80aa48190884bab800f357106 |
completed | April 14, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69de657359c88190b082e3e9f86fc1d7 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:26 a.m.