Triple

T11914813
Position Surface form Disambiguated ID Type / Status
Subject Codex Theodosianus E283489 entity
Predicate follows P134 FINISHED
Object Codex Gregorianus E156219 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: Codex Gregorianus | Statement: [Codex Theodosianus, follows, Codex Gregorianus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Codex Gregorianus
Context triple: [Codex Theodosianus, follows, Codex Gregorianus]
  • A. Codex Gregorianus chosen
    The Codex Gregorianus is an early 4th-century private compilation of Roman imperial constitutions that became a foundational source for later official law codes.
  • B. Codex Marianus
    Codex Marianus is an early Old Church Slavonic Gospel manuscript, written in the Glagolitic script and considered one of the most important monuments of Slavic medieval literature.
  • C. Codex Basilensis
    Codex Basilensis is a significant Greek New Testament manuscript known for its representative Byzantine text-type and its importance in biblical textual criticism.
  • D. Codex Vercellensis
    Codex Vercellensis is an early medieval manuscript best known for preserving a collection of Old English religious poetry, including "The Dream of the Rood," within the Vercelli Book.
  • E. Codex Carolinus
    Codex Carolinus is a 6th- or 7th-century bilingual manuscript fragment preserving portions of the Gothic and Latin texts of the Bible, making it an important source for the study of the Gothic language and early biblical transmission.
  • 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_69d6ab2c07e88190ba13b0d21fd6cf33 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8e52a2bc08190b80cc6ccf5779d7c completed April 10, 2026, 11:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69f4186938548190b5ae10e111aece9a completed May 1, 2026, 3:05 a.m.
Created at: April 8, 2026, 9:44 p.m.