Triple

T13074725
Position Surface form Disambiguated ID Type / Status
Subject Constantine V E329542 entity
Predicate spouse P13 FINISHED
Object Maria
Maria was a Byzantine empress consort, known primarily as the wife of Emperor Constantine V in the 8th-century Byzantine Empire.
 E1027500 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: Maria | Statement: [Constantine V, spouse, Maria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maria
Context triple: [Constantine V, spouse, Maria]
  • A. Maria
    Maria is a track on Rage Against the Machine’s 2000 album "The Battle of Los Angeles," known for its politically charged lyrics and aggressive rap metal sound.
  • B. Maria
    Maria is an Italian woman best known as the younger sister of actress Sophia Loren and the former wife of film producer Romano Mussolini.
  • C. Maria
    Maria is a witty and sharp-tongued gentlewoman in Olivia’s household in Shakespeare’s comedy "Twelfth Night," known for her clever schemes and playful manipulation of other characters.
  • D. Maria
    Maria is a coastal municipality on Siquijor Island in the Philippines known for its rural communities and scenic seaside landscapes.
  • E. Maria
    Maria is a central character in Fritz Lang's classic science fiction film "Metropolis," known for her compassionate leadership and symbolic role as a mediator between social classes.
  • 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: Maria
Triple: [Constantine V, spouse, Maria]
Generated description
Maria was a Byzantine empress consort, known primarily as the wife of Emperor Constantine V in the 8th-century Byzantine Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maria
Target entity description: Maria was a Byzantine empress consort, known primarily as the wife of Emperor Constantine V in the 8th-century Byzantine Empire.
  • A. Maria
    Maria was a Byzantine empress consort and the mother of Emperor Constantine V in the 8th-century Byzantine Empire.
  • B. Maria
    Maria was a late Roman noblewoman of the Western Roman Empire, known primarily as the daughter of the powerful general Stilicho and wife of Emperor Honorius.
  • C. Maria
    Maria is a Russian noblewoman of the late 16th century, known as the wife of Tsar Boris Godunov and Tsaritsa of Russia.
  • D. Maria
    Maria is the given name of Maria Ludovika of Austria-Este, an Empress consort of Austria in the early 19th century.
  • E. Maria
    Maria is a Russian grand duchess of the Romanov dynasty, known as Maria Mikhailovna of Russia.
  • 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_69d80771749c81909a6d9197b9504872 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d98117209081908272021013df2222 completed April 10, 2026, 11 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5cafd6c81908cb16bc0129ae74e completed May 3, 2026, 7:14 a.m.
NEDg Description generation batch_69f6f8df46508190b31ee0f5272df05f completed May 3, 2026, 7:27 a.m.
NED2 Entity disambiguation (via description) batch_69f6fa323f288190909492ce610007a4 completed May 3, 2026, 7:33 a.m.
Created at: April 9, 2026, 9 p.m.