Triple

T953658
Position Surface form Disambiguated ID Type / Status
Subject Muspilli E20577 entity
Predicate manuscriptType P21654 FINISHED
Object single manuscript witness LITERAL 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: single manuscript witness | Statement: [Muspilli, manuscriptType, single manuscript witness]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: manuscriptType
Context triple: [Muspilli, manuscriptType, single manuscript witness]
  • A. manuscript
    Indicates that an entity is a written or typed document, often a draft or original version of a text, associated with another entity (such as its author, subject, or publication process).
  • B. publicationType
    Indicates the specific category or format of a published work that characterizes how it is issued or presented.
  • C. manuscriptTradition
    Indicates the relationship between a text and the chain of manuscript copying, transmission, and variation through which that text has been preserved and passed down.
  • D. manuscriptShelfmark
    Indicates the specific shelfmark or call number under which a manuscript is stored or cataloged in a collection.
  • E. draftType
    Indicates the specific category or kind of draft associated with an entity or document (e.g., initial, revised, or final draft).
  • F. None of above. chosen

Provenance (4 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_69a493b0f2fc81908cd227480a5356a1 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3d8f2e0819097554a301f8aa70f completed March 1, 2026, 9:47 p.m.
PD Predicate disambiguation batch_69a4b2a045308190ab94f3adab40db8d completed March 1, 2026, 9:41 p.m.
PDg Predicate description generation batch_69a4b30efd2c8190b780a6dee086d0aa completed March 1, 2026, 9:43 p.m.
Created at: March 1, 2026, 7:40 p.m.