Triple

T21626718
Position Surface form Disambiguated ID Type / Status
Subject Justitia E533723 entity
Predicate hasLatinName P3646 FINISHED
Object Iustitia NE NERFINISHED

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: Iustitia | Statement: [Justitia, hasLatinName, Iustitia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iustitia
Context triple: [Justitia, hasLatinName, Iustitia]
  • A. Justitia chosen
    Justitia is the Roman goddess of justice, law, and fairness, typically depicted with scales and a sword to symbolize impartial judgment and authority.
  • B. Justa
    Justa was a daughter of the Roman emperor Valentinian I, belonging to the imperial family of the late Western Roman Empire.
  • C. Justitia Omnibus
    Justitia Omnibus is the Latin motto of Washington, D.C., meaning "Justice for All."
  • D. Grand Justice
    Grand Justice is a high-ranking constitutional judge serving on Taiwan’s Judicial Yuan, responsible for interpreting the Constitution and overseeing constitutional matters.
  • E. Mirror of justice
    Mirror of justice is a Marian title from the Litany of Loreto that honors the Virgin Mary as the perfect reflection of God’s justice and holiness.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef52131f2c8190b9966adf43a0fe4f completed April 27, 2026, 12:09 p.m.
Created at: April 16, 2026, 6:34 p.m.