Triple

T15838561
Position Surface form Disambiguated ID Type / Status
Subject Köroghlu E384042 entity
Predicate moralAlignmentInLegend P22459 FINISHED
Object champion of the oppressed 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: champion of the oppressed | Statement: [Köroghlu, moralAlignmentInLegend, champion of the oppressed]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: moralAlignmentInLegend
Context triple: [Köroghlu, moralAlignmentInLegend, champion of the oppressed]
  • A. characterAlignment chosen
    Indicates the moral or ethical stance a character holds, typically along axes such as good–evil and lawful–chaotic.
  • B. speciesAlignment
    Indicates how closely related or compatible two species are in terms of traits, behavior, or evolutionary relationship.
  • C. primaryRaceAlignment
    Indicates how an entity’s main racial identity or classification is aligned, categorized, or associated within a defined racial framework or system.
  • D. hasMoralArchetype
    Indicates that an entity exemplifies or is characterized by a particular moral pattern, role, or ethical archetype.
  • E. isMoralFoilFor
    Indicates that one entity serves as a contrasting counterpart whose differing moral qualities highlight or emphasize the moral traits of another entity.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142e4fa24819086a1a226082ac2d3 completed April 16, 2026, 8:13 p.m.
PD Predicate disambiguation batch_69e005418f588190824d91ff7974dada completed April 15, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:49 a.m.