Triple

T13906925
Position Surface form Disambiguated ID Type / Status
Subject Mancunium E334376 entity
Predicate language P15 FINISHED
Object Latin E5875 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: Latin | Statement: [Mancunium, language, Latin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latin
Context triple: [Mancunium, language, Latin]
  • A. Latin chosen
    Latin is an ancient Italic language of the Roman Empire that profoundly shaped the vocabulary, grammar, and development of many European languages and scholarly traditions.
  • B. Latin I
    Latin I is an introductory course in the Latin language that typically covers basic grammar, vocabulary, and reading skills while introducing students to aspects of ancient Roman culture.
  • C. Latin Lingo
    "Latin Lingo" is a bilingual hip hop track by Cypress Hill that showcases their signature fusion of English and Spanish lyrics over a gritty, funk-influenced beat.
  • D. Old Latin
    Old Latin is the early form of the Latin language used in ancient Rome before the Classical period, preserved in archaic inscriptions and early literary texts.
  • E. Classical Latin
    Classical Latin is the standardized form of the Latin language used in ancient Roman literature, oratory, and formal writing during the late Republic and early Empire.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de25dc26cc8190a7909980b1d34933 completed April 14, 2026, 11:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c724c6188190ae0c2784c3b48a12 completed May 3, 2026, 10:07 p.m.
Created at: April 9, 2026, 10:16 p.m.