Triple

T17973535
Position Surface form Disambiguated ID Type / Status
Subject Two-Face E449405 entity
Predicate formerMoralAlignment P22459 FINISHED
Object lawful 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: lawful | Statement: [Two-Face, formerMoralAlignment, lawful]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerMoralAlignment
Context triple: [Two-Face, formerMoralAlignment, lawful]
  • A. characterAlignment chosen
    Indicates the moral or ethical stance a character holds, typically along axes such as good–evil and lawful–chaotic.
  • B. isMoralFoilFor
    Indicates that one entity serves as a contrasting counterpart whose differing moral qualities highlight or emphasize the moral traits of another entity.
  • C. hasMoralArchetype
    Indicates that an entity exemplifies or is characterized by a particular moral pattern, role, or ethical archetype.
  • D. moralAttitude
    Indicates a subject’s evaluative stance or judgment about the moral rightness or wrongness of another entity, action, or situation.
  • E. speciesAlignment
    Indicates how closely related or compatible two species are in terms of traits, behavior, or evolutionary relationship.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b1fca04481908f0dd875953fd82f completed April 19, 2026, 10:44 a.m.
PD Predicate disambiguation batch_69e3f8fa62688190a5d5c361ab896256 completed April 18, 2026, 9:34 p.m.
Created at: April 10, 2026, 10:22 a.m.