Triple

T6015722
Position Surface form Disambiguated ID Type / Status
Subject Proserpine E133944 entity
Predicate hasCharacter P2308 FINISHED
Object Démons E146646 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: Démons | Statement: [Proserpine, hasCharacter, Démons]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Démons
Context triple: [Proserpine, hasCharacter, Démons]
  • A. Demons
    The Demons are the nickname of the Melbourne Football Club, one of the oldest and most storied teams in Australian rules football.
  • B. Demons chosen
    Demons is a political and psychological novel by Fyodor Dostoevsky that explores radicalism, moral chaos, and the destructive consequences of nihilist ideology in 19th-century Russia.
  • C. Demons
    "Demons" is a drill-rap track by Fivio Foreign that helped establish his presence in the New York drill scene with its dark production and aggressive delivery.
  • D. Demons
    "Demons" is a track by British electronic musician Fatboy Slim, featured on his 2000 album "Halfway Between the Gutter and the Stars."
  • E. Shaitan
    Shaitan is a figure in Islamic belief commonly identified as the Devil, representing evil, temptation, and rebellion against God.
  • 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_69c0087361a48190905c6b55969852b8 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04f80ec108190ae9711727debb061 completed March 22, 2026, 8:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c108ade3948190994fbaa2a5539216 completed March 23, 2026, 9:32 a.m.
Created at: March 22, 2026, 4:06 p.m.