Triple

T29315758
Position Surface form Disambiguated ID Type / Status
Subject Book Four: Balance E743370 entity
Predicate hasCharacter P2308 FINISHED
Object Prince Wu
Prince Wu is the immature yet ultimately reform-minded heir to the Earth Kingdom throne in The Legend of Korra’s fourth season, Book Four: Balance.
E1864832 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: Prince Wu | Statement: [Book Four: Balance, hasCharacter, Prince Wu]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Prince Wu
Triple: [Book Four: Balance, hasCharacter, Prince Wu]
Generated description
Prince Wu is the immature yet ultimately reform-minded heir to the Earth Kingdom throne in The Legend of Korra’s fourth season, Book Four: Balance.

Provenance (5 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_69f0912502c8819087d9e8398ee991a8 completed April 28, 2026, 10:51 a.m.
NER Named-entity recognition batch_69f665ec3ee481909ae35e76899a7056 completed May 2, 2026, 9 p.m.
NED1 Entity disambiguation (via context triple) batch_6a25c0e88904819091cd0e5476547c82 completed June 7, 2026, 7:05 p.m.
NEDg Description generation batch_6a25c5320dcc8190a952a813227cc432 completed June 7, 2026, 7:23 p.m.
NED2 Entity disambiguation (via description) batch_6a25ca42d1f08190a6b399b64806cf2f completed June 7, 2026, 7:45 p.m.
Created at: April 28, 2026, 1:19 p.m.