Triple
T8511492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avatar: The Last Airbender |
E201463
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Sokka |
E343741
|
NE 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: Sokka | Statement: [Avatar: The Last Airbender, mainCharacter, Sokka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sokka Context triple: [Avatar: The Last Airbender, mainCharacter, Sokka]
-
A.
Sokka
chosen
Sokka is a main character from the animated series "Avatar: The Last Airbender," known as a boomerang-wielding, sarcastic strategist and warrior of the Southern Water Tribe.
-
B.
Kai
Kai is the fictional half-Japanese, half-English outcast and skilled warrior portrayed by Keanu Reeves in the fantasy samurai film "47 Ronin."
-
C.
Kai
Kai is a masculine given name used in various cultures, often associated with meanings such as "sea," "forgiveness," or "victory" depending on its linguistic origin.
-
D.
Kai
Kai is the supernatural yak warrior and primary antagonist in the animated film "Kung Fu Panda 3."
-
E.
Kai
Kai is the eldest granddaughter of former U.S. President Donald Trump and the daughter of Donald Trump Jr.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe608e5b08190a6d551793e8ed94b |
completed | March 31, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4e47542c8190af93dca3ce16a04b |
completed | April 2, 2026, 11:08 a.m. |
Created at: March 30, 2026, 6:15 p.m.