Triple

T29791641
Position Surface form Disambiguated ID Type / Status
Subject Keith E756422 entity
Predicate affiliation P10 FINISHED
Object Blade of Marmora
The Blade of Marmora is a secretive Galra rebel organization in Voltron: Legendary Defender that opposes the Galra Empire from within through espionage and covert operations.
E1885069 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: Blade of Marmora | Statement: [Keith, affiliation, Blade of Marmora]
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: Blade of Marmora
Triple: [Keith, affiliation, Blade of Marmora]
Generated description
The Blade of Marmora is a secretive Galra rebel organization in Voltron: Legendary Defender that opposes the Galra Empire from within through espionage and covert operations.

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_69f22454583081908927516cb9938d1d completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f674e2ada081908511761af8eaa114 completed May 2, 2026, 10:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a26c90898bc8190b57c51f4982f980d completed June 8, 2026, 1:52 p.m.
NEDg Description generation batch_6a26cd43832c819092f8bc754b39c134 completed June 8, 2026, 2:10 p.m.
NED2 Entity disambiguation (via description) batch_6a26db51b0a08190ba22629669e8fbc2 completed June 8, 2026, 3:10 p.m.
Created at: April 29, 2026, 5:12 p.m.