Triple

T2297544
Position Surface form Disambiguated ID Type / Status
Subject Tosefta E51651 entity
Predicate hasManuscript P16604 FINISHED
Object Erfurt manuscript
The Erfurt manuscript is one of the principal medieval Hebrew manuscripts preserving the text of the Tosefta, making it a key source for the study of early rabbinic literature.
E255255 NE FINISHED

How this triple was built (4 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: Erfurt manuscript | Statement: [Tosefta, hasManuscript, Erfurt manuscript]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erfurt manuscript
Context triple: [Tosefta, hasManuscript, Erfurt manuscript]
  • A. Vienna manuscript
    The Vienna manuscript is a significant medieval handwritten copy of the Tosefta, valued by scholars as one of the primary textual witnesses to this early rabbinic work.
  • B. Codex Forster
    Codex Forster is a collection of Leonardo da Vinci’s notebooks containing his sketches, scientific studies, and writings on a wide range of subjects.
  • C. Codex Boturini
    Codex Boturini is a pre-Hispanic Aztec pictorial manuscript that chronicles the Mexica migration and the legendary origins of Tenochtitlan.
  • D. Codex Becker I
    Codex Becker I is a pre-Columbian Mixtec pictographic manuscript that records genealogies, rituals, and historical events of Mixtec nobility in what is now southern Mexico.
  • E. Codex Trivulzianus
    Codex Trivulzianus is a manuscript notebook by Leonardo da Vinci containing his studies in language, engineering, and various scientific and artistic subjects.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Erfurt manuscript
Triple: [Tosefta, hasManuscript, Erfurt manuscript]
Generated description
The Erfurt manuscript is one of the principal medieval Hebrew manuscripts preserving the text of the Tosefta, making it a key source for the study of early rabbinic literature.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Erfurt manuscript
Target entity description: The Erfurt manuscript is one of the principal medieval Hebrew manuscripts preserving the text of the Tosefta, making it a key source for the study of early rabbinic literature.
  • A. Vienna manuscript
    The Vienna manuscript is a significant medieval handwritten copy of the Tosefta, valued by scholars as one of the primary textual witnesses to this early rabbinic work.
  • B. Codex Forster
    Codex Forster is a collection of Leonardo da Vinci’s notebooks containing his sketches, scientific studies, and writings on a wide range of subjects.
  • C. Codex Boturini
    Codex Boturini is a pre-Hispanic Aztec pictorial manuscript that chronicles the Mexica migration and the legendary origins of Tenochtitlan.
  • D. Codex Becker I
    Codex Becker I is a pre-Columbian Mixtec pictographic manuscript that records genealogies, rituals, and historical events of Mixtec nobility in what is now southern Mexico.
  • E. Codex Trivulzianus
    Codex Trivulzianus is a manuscript notebook by Leonardo da Vinci containing his studies in language, engineering, and various scientific and artistic subjects.
  • F. None of above. chosen

Provenance (5 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_69a88b0a9f248190bcff941463d8f65a completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abd0d6b0e48190aee9131ca182e52f completed March 7, 2026, 7:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae8954a804819092c716582f23af14 completed March 9, 2026, 8:48 a.m.
NEDg Description generation batch_69ae8b188f18819088eaa3866485191a completed March 9, 2026, 8:55 a.m.
NED2 Entity disambiguation (via description) batch_69ae8b83efd48190a832032775803919 completed March 9, 2026, 8:57 a.m.
Created at: March 4, 2026, 7:49 p.m.