Triple

T33351856
Position Surface form Disambiguated ID Type / Status
Subject Our Lady of Luján E853963 entity
Predicate earlyCustodian P114319 FINISHED
Object Ana de Matos
Ana de Matos was an early lay caretaker associated with the veneration and safeguarding of the Marian image of Our Lady of Luján in Argentina.
 E2046785 NE FINISHED

How this triple was built (3 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: Ana de Matos | Statement: [Our Lady of Luján, earlyCustodian, Ana de Matos]
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: Ana de Matos
Triple: [Our Lady of Luján, earlyCustodian, Ana de Matos]
Generated description
Ana de Matos was an early lay caretaker associated with the veneration and safeguarding of the Marian image of Our Lady of Luján in Argentina.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: earlyCustodian
Context triple: [Our Lady of Luján, earlyCustodian, Ana de Matos]
  • A. earlyRepresentative
    Indicates that one entity serves as an initial or pioneering representative or example of another entity in time or development.
  • B. earlyUse
    Indicates that an entity is used or adopted at an unusually early time or stage relative to a typical or expected point of use.
  • C. traditionalCustodianOf chosen
    Indicates that an entity holds recognized traditional responsibility, authority, or guardianship over another entity, often in a cultural, ancestral, or customary context.
  • D. earlyVersion
    Indicates that one entity is an earlier or preliminary version of another entity in a version sequence.
  • E. earlyProduct
    Indicates that one entity is an initial or early version of a product in relation to another 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_69f3496acbc8819099fd0305ecc42080 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6ffbad8848190867c2988c0ceb84f completed May 3, 2026, 7:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a35520ce0348190acc5e5fb6fba4927 completed June 19, 2026, 2:28 p.m.
NEDg Description generation batch_6a3554d93bf88190a81d58f8a7bd34ee completed June 19, 2026, 2:40 p.m.
NED2 Entity disambiguation (via description) batch_6a35553aa3d08190842c0f1200ad9419 completed June 19, 2026, 2:42 p.m.
PD Predicate disambiguation batch_69f6fc5740fc81909774a4f65201a3ff completed May 3, 2026, 7:42 a.m.
Created at: May 1, 2026, 1:34 a.m.