Triple

T22860123
Position Surface form Disambiguated ID Type / Status
Subject CIL XIII E566891 entity
Predicate series P1761 FINISHED
Object Corpus Inscriptionum Latinarum 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: Corpus Inscriptionum Latinarum | Statement: [CIL XIII, series, Corpus Inscriptionum Latinarum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corpus Inscriptionum Latinarum
Context triple: [CIL XIII, series, Corpus Inscriptionum Latinarum]
  • A. Corpus Inscriptionum Latinarum chosen
    Corpus Inscriptionum Latinarum is a comprehensive scholarly collection and critical edition of ancient Latin inscriptions from across the Roman world.
  • B. Corpus Inscriptionum Graecarum
    Corpus Inscriptionum Graecarum is a foundational 19th-century scholarly collection of ancient Greek inscriptions that significantly advanced the study of Greek epigraphy and history.
  • C. Thesaurus linguae latinae
    Thesaurus linguae latinae is a landmark Latin dictionary and lexicographical work compiled by the 16th-century French scholar and printer Robert Estienne.
  • D. Commentarii linguae Latinae
    Commentarii linguae Latinae is a 16th-century Latin grammar and commentary work by French humanist Étienne Dolet, reflecting Renaissance scholarship on the Latin language.
  • E. Corpus Tibullianum
    Corpus Tibullianum is a collection of Latin elegiac poetry traditionally attributed to the Roman poet Tibullus and associated authors.
  • 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_69e24589083081908d5694c4fdc80086 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17ec082c08190943e6cfc2e25c5cc completed April 29, 2026, 3:45 a.m.
Created at: April 17, 2026, 3:37 p.m.