Triple

T15148541
Position Surface form Disambiguated ID Type / Status
Subject Historia Langobardorum E361876 entity
Predicate hasManuscriptWitness P20000 FINISHED
Object Codex Sangallensis 635
Codex Sangallensis 635 is a medieval manuscript preserved at the Abbey Library of Saint Gall that contains an important copy of Paul the Deacon’s *Historia Langobardorum*, a key narrative source on the history of the Lombards.
E1140873 NE FINISHED

How this triple was built (5 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 Sangallensis 635 | Statement: [Historia Langobardorum, hasManuscriptWitness, Codex Sangallensis 635]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Codex Sangallensis 635
Context triple: [Historia Langobardorum, hasManuscriptWitness, Codex Sangallensis 635]
  • A. Codex Calixtinus
    Codex Calixtinus is a 12th-century illuminated manuscript that serves as one of the earliest and most important narrative, liturgical, and practical sources for pilgrims traveling the Camino de Santiago.
  • B. Codex Arundel
    Codex Arundel is a celebrated collection of Leonardo da Vinci’s scientific and artistic notes and drawings, showcasing his investigations into mechanics, geometry, and natural phenomena.
  • C. Codex Washingtonensis
    Codex Washingtonensis is an early Greek manuscript of the four Gospels, notable for its mixed text-type and importance in New Testament textual criticism.
  • D. Codex Selden
    Codex Selden is a pre-Hispanic Mixtec pictorial manuscript that records genealogies, dynastic histories, and ritual information from the Mixtec civilization of what is now southern Mexico.
  • E. Codex Boturini
    Codex Boturini is a pre-Hispanic Aztec pictorial manuscript that chronicles the Mexica migration and the legendary origins of Tenochtitlan.
  • 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: Codex Sangallensis 635
Triple: [Historia Langobardorum, hasManuscriptWitness, Codex Sangallensis 635]
Generated description
Codex Sangallensis 635 is a medieval manuscript preserved at the Abbey Library of Saint Gall that contains an important copy of Paul the Deacon’s *Historia Langobardorum*, a key narrative source on the history of the Lombards.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Codex Sangallensis 635
Target entity description: Codex Sangallensis 635 is a medieval manuscript preserved at the Abbey Library of Saint Gall that contains an important copy of Paul the Deacon’s *Historia Langobardorum*, a key narrative source on the history of the Lombards.
  • A. Codex Calixtinus
    Codex Calixtinus is a 12th-century illuminated manuscript that serves as one of the earliest and most important narrative, liturgical, and practical sources for pilgrims traveling the Camino de Santiago.
  • B. Codex Arundel
    Codex Arundel is a celebrated collection of Leonardo da Vinci’s scientific and artistic notes and drawings, showcasing his investigations into mechanics, geometry, and natural phenomena.
  • C. Codex Washingtonensis
    Codex Washingtonensis is an early Greek manuscript of the four Gospels, notable for its mixed text-type and importance in New Testament textual criticism.
  • D. Codex Selden
    Codex Selden is a pre-Hispanic Mixtec pictorial manuscript that records genealogies, dynastic histories, and ritual information from the Mixtec civilization of what is now southern Mexico.
  • E. Codex Boturini
    Codex Boturini is a pre-Hispanic Aztec pictorial manuscript that chronicles the Mexica migration and the legendary origins of Tenochtitlan.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasManuscriptWitness
Context triple: [Historia Langobardorum, hasManuscriptWitness, Codex Sangallensis 635]
  • A. manuscriptWitness chosen
    Indicates that one entity serves as a manuscript witness (a specific physical manuscript or copy) that attests to or preserves the text of another entity.
  • B. areManuscriptsOf
    Indicates that the subject entities are manuscripts that are versions, copies, or instances of the work represented by the object entity.
  • C. copiedManuscriptsOf
    Indicates that one entity has produced or created handwritten reproductions of the manuscripts belonging to another entity.
  • D. hasManuscriptsIn
    Indicates that an entity possesses or is associated with manuscripts that are located in a specified place or collection.
  • E. manuscriptDiscoveredBy
    Indicates that a manuscript was found or brought to light through the efforts or actions of a particular agent or entity.
  • F. None of above.

Provenance (6 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_69d85a0759908190b8a051d2e2a1cbe6 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005c825a481909d00098b0e743365 completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69febff281848190a094bd697b19aaf3 completed May 9, 2026, 5:02 a.m.
NEDg Description generation batch_69fec3becbe08190a3a3517830cef461 completed May 9, 2026, 5:18 a.m.
NED2 Entity disambiguation (via description) batch_69fec41e15d48190a44ddf901fdcca3e completed May 9, 2026, 5:20 a.m.
PD Predicate disambiguation batch_69deb9713fe881909dec2fd3f6c84b39 completed April 14, 2026, 10:02 p.m.
Created at: April 10, 2026, 3:07 a.m.