Triple

T23432707
Position Surface form Disambiguated ID Type / Status
Subject CIL VIII E563374 entity
Predicate belongsToSeries P4276 FINISHED
Object Corpus Inscriptionum Latinarum main series 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 main series | Statement: [CIL VIII, belongsToSeries, Corpus Inscriptionum Latinarum main series]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corpus Inscriptionum Latinarum main series
Context triple: [CIL VIII, belongsToSeries, Corpus Inscriptionum Latinarum main series]
  • 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. 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.
  • D. Corpus Tibullianum
    Corpus Tibullianum is a collection of Latin elegiac poetry traditionally attributed to the Roman poet Tibullus and associated authors.
  • E. Corpus Agrimensorum Romanorum
    The Corpus Agrimensorum Romanorum is a collection of late Roman technical writings on land surveying, boundary marking, and related legal-administrative practices.
  • 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_69e24553980c8190bb66a2ae0bdab125 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a5d920548190904f80c7c40cba06 completed April 29, 2026, 6:31 a.m.
Created at: April 17, 2026, 5:49 p.m.