Triple
T29136887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fire Lord Ozai |
E738531
|
entity |
| Predicate | bendingSpecialty |
P119495
|
FINISHED |
| Object | lightning generation |
—
|
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: lightning generation | Statement: [Fire Lord Ozai, bendingSpecialty, lightning generation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bendingSpecialty Context triple: [Fire Lord Ozai, bendingSpecialty, lightning generation]
-
A.
bendingSubskill
chosen
Indicates a specific skill or technique that forms part of the broader ability to bend or flex something.
-
B.
bendingStyle
Indicates the manner or technique by which something is bent or flexed.
-
C.
craftSpecialty
Indicates that an entity has a particular area of specialized skill or focus within a craft or artisanal practice.
-
D.
materialSpecialization
Indicates a relationship where one material is a specialized, more specific, or refined form of another more general material.
-
E.
productionTypeSpecialization
Indicates a relationship where one production type is a more specific or specialized form of another, broader production type.
- 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6626b8aa881908e1bf4776c2feea9 |
completed | May 2, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:34 a.m.