Triple

T15537584
Position Surface form Disambiguated ID Type / Status
Subject Mária E370388 entity
Predicate hasItalianEquivalent P48373 FINISHED
Object Maria
Maria is a widely used female given name of Hebrew origin, common across many languages and cultures, particularly in Christian traditions.
E103006 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: Maria | Statement: [Mária, hasItalianEquivalent, Maria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria
Context triple: [Mária, hasItalianEquivalent, Maria]
  • A. 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.
  • B. Maria
    Maria is a character in the period drama film "Stage Beauty," which explores gender roles and the world of 17th-century English theatre.
  • C. 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.
  • D. Maria
    Maria I of Portugal was the first queen regnant of Portugal, known for her devout Catholicism, initial period of enlightened reforms, and later mental illness that led to her son acting as regent.
  • E. Maria
    Maria is a witty and sharp-tongued lady-in-waiting to the Princess of France in William Shakespeare’s comedy "Love's Labour's Lost."
  • 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: [Mária, hasItalianEquivalent, Maria]
Generated description
Maria is a widely used female given name of Hebrew origin, common across many languages and cultures, particularly in Christian traditions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maria
Target entity description: Maria is a widely used female given name of Hebrew origin, common across many languages and cultures, particularly in Christian traditions.
  • A. Maria chosen
    Maria is a female given name of Latin origin meaning "beloved" or "wished-for child," widely used across many cultures and languages.
  • B. Maria
    Maria is the given name of Maria Christina of the Netherlands, a 19th-century Dutch princess and member of the House of Orange-Nassau.
  • C. Maria
    Maria is a woman known primarily as the daughter of Theophilus.
  • D. Maria
    Maria is the given name of Anna Maria Spencer-Stanhope, a member of the English Spencer-Stanhope family.
  • E. Maria
    Maria is the given name of Maria Ludovika of Austria-Este, an Empress consort of Austria in the early 19th century.
  • F. None of above.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasItalianEquivalent
Context triple: [Mária, hasItalianEquivalent, Maria]
  • A. equivalentTitleInItalian chosen
    Indicates that one entity’s title is an equivalent version of another entity’s title expressed in Italian.
  • B. ItalianVersionClaimed
    Indicates that an entity asserts or is reported to have an Italian-language version.
  • C. ItalianObjective
    Indicates that an entity has an objective, goal, or target specifically related to Italy or the Italian context.
  • D. cognateInItalian
    Indicates that a word has a cognate (a related word with a common etymological origin) in Italian.
  • E. equivalentIn
    Indicates that two entities are considered logically or functionally the same in meaning, status, or effect within a given context.
  • 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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e0442f3c688190a599165e526af2ed completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f2d4b1c81909ff876289db20803 completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff604e1b0c819092fc17b00f5797b3 completed May 9, 2026, 4:26 p.m.
NED2 Entity disambiguation (via description) batch_69ff60fb6f048190b02917a4f2f1a83d completed May 9, 2026, 4:29 p.m.
PD Predicate disambiguation batch_69deda7a95c48190bbe29fadcf17191a completed April 15, 2026, 12:23 a.m.
Created at: April 10, 2026, 4:06 a.m.