Triple

T5380278
Position Surface form Disambiguated ID Type / Status
Subject Ascanius E113063 entity
Predicate relatedFigure P37 FINISHED
Object Remus E496789 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: Remus | Statement: [Ascanius, relatedFigure, Remus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Remus
Context triple: [Ascanius, relatedFigure, Remus]
  • A. Remus chosen
    Remus is a male given name best known from the Harry Potter character Remus Lupin and the mythological twin of Romulus in Roman legend.
  • B. Loup
    The Loup is a river in southeastern France that flows through the Alpes-Maritimes department, known for its scenic gorges and popular outdoor recreation areas.
  • C. Cerbère
    Cerbère is a coastal commune in southern France near the Spanish border, known for its Mediterranean scenery and winegrowing tradition.
  • D. Luppi
    Luppi is a surname most notably associated with Argentine actor Federico Luppi, renowned for his work in Latin American and Spanish cinema.
  • E. Roman the Bear
    Roman the Bear is the official mascot of the University of Bath, typically depicted as a friendly bear symbolizing the university’s spirit and community.
  • 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_69bd4436a1988190af18dcff7fd306b4 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd86ce56c88190a66b3852416edccb completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf2949cd9881908ca0d8fdf1642f71 completed March 21, 2026, 11:27 p.m.
Created at: March 20, 2026, 2:03 p.m.