Triple

T3442494
Position Surface form Disambiguated ID Type / Status
Subject Funeral Sermon and Prayer E72596 entity
Predicate containedIn P40 FINISHED
Object Pray Codex
The Pray Codex is a late 12th-century Hungarian manuscript notable for containing some of the earliest known continuous texts in the Hungarian language and one of the oldest surviving depictions of the burial of Christ.
 E357088 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: Pray Codex | Statement: [Funeral Sermon and Prayer, containedIn, Pray Codex]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pray Codex
Context triple: [Funeral Sermon and Prayer, containedIn, Pray Codex]
  • A. Codex Mendoza
    The Codex Mendoza is a 16th-century Aztec manuscript created shortly after the Spanish conquest that documents Mexica history, tribute, and daily life for colonial authorities.
  • B. Maya codices
    The Maya codices are a small surviving collection of pre-Columbian bark-paper books that record the ancient Maya’s astronomical, calendrical, and ritual knowledge.
  • C. Florentine Codex
    The Florentine Codex is a 16th-century encyclopedic manuscript compiled by Bernardino de Sahagún that documents Aztec culture, language, religion, and history in both Nahuatl and Spanish.
  • D. Codex Vindobonensis Mexicanus I
    Codex Vindobonensis Mexicanus I is a pre-Columbian Mixtec pictorial manuscript that records genealogies, rituals, and mytho-historical narratives of Mixtec rulers and deities.
  • E. Madrid Codices
    The Madrid Codices are a set of Leonardo da Vinci’s rediscovered notebooks containing detailed studies of mechanics, geometry, and engineering, offering crucial insight into his scientific and technical genius.
  • 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: Pray Codex
Triple: [Funeral Sermon and Prayer, containedIn, Pray Codex]
Generated description
The Pray Codex is a late 12th-century Hungarian manuscript notable for containing some of the earliest known continuous texts in the Hungarian language and one of the oldest surviving depictions of the burial of Christ.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pray Codex
Target entity description: The Pray Codex is a late 12th-century Hungarian manuscript notable for containing some of the earliest known continuous texts in the Hungarian language and one of the oldest surviving depictions of the burial of Christ.
  • A. Codex Mendoza
    The Codex Mendoza is a 16th-century Aztec manuscript created shortly after the Spanish conquest that documents Mexica history, tribute, and daily life for colonial authorities.
  • B. Maya codices
    The Maya codices are a small surviving collection of pre-Columbian bark-paper books that record the ancient Maya’s astronomical, calendrical, and ritual knowledge.
  • C. Florentine Codex
    The Florentine Codex is a 16th-century encyclopedic manuscript compiled by Bernardino de Sahagún that documents Aztec culture, language, religion, and history in both Nahuatl and Spanish.
  • D. Codex Vindobonensis Mexicanus I
    Codex Vindobonensis Mexicanus I is a pre-Columbian Mixtec pictorial manuscript that records genealogies, rituals, and mytho-historical narratives of Mixtec rulers and deities.
  • E. Madrid Codices
    The Madrid Codices are a set of Leonardo da Vinci’s rediscovered notebooks containing detailed studies of mechanics, geometry, and engineering, offering crucial insight into his scientific and technical genius.
  • 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_69ad85b05c848190b7a28ceec2bd7b74 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adba28ec448190a6a07c5f16235fe3 completed March 8, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69b35486f7a08190885e98bb89e74f15 completed March 13, 2026, 12:04 a.m.
NEDg Description generation batch_69b35547a9a881909d754625806cff2a completed March 13, 2026, 12:07 a.m.
NED2 Entity disambiguation (via description) batch_69b355efa89c8190bf9b2eb3c41257b3 completed March 13, 2026, 12:10 a.m.
Created at: March 8, 2026, 3:16 p.m.