Triple

T13658323
Position Surface form Disambiguated ID Type / Status
Subject Maria de Luna E326918 entity
Predicate mother P120 FINISHED
Object Brianda d’Agout
Brianda d’Agout was a noblewoman of the late 14th century, best known as the mother of Maria de Luna, queen consort of Aragon.
E1052604 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: Brianda d’Agout | Statement: [Maria de Luna, mother, Brianda d’Agout]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brianda d’Agout
Context triple: [Maria de Luna, mother, Brianda d’Agout]
  • A. Bachué
    Bachué is a principal mother goddess in Muisca mythology, associated with creation, fertility, and the origin of humanity.
  • B. Zibelle
    Zibelle is a village in eastern Germany, historically part of Lusatia, known in this context as the place where physicist Walther Nernst died.
  • C. Alvier
    Alvier is a prominent mountain peak in the Churfirsten range of the Swiss Alps, known for its scenic hiking routes and panoramic views.
  • D. Vachon
    Vachon is a French-origin surname borne by various notable individuals, including artists, athletes, and public figures.
  • E. Manguin
    Manguin is the surname of Henri Manguin, a French Fauvist painter known for his vibrant use of color and Mediterranean scenes.
  • 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: Brianda d’Agout
Triple: [Maria de Luna, mother, Brianda d’Agout]
Generated description
Brianda d’Agout was a noblewoman of the late 14th century, best known as the mother of Maria de Luna, queen consort of Aragon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brianda d’Agout
Target entity description: Brianda d’Agout was a noblewoman of the late 14th century, best known as the mother of Maria de Luna, queen consort of Aragon.
  • A. Bachué
    Bachué is a principal mother goddess in Muisca mythology, associated with creation, fertility, and the origin of humanity.
  • B. Zibelle
    Zibelle is a village in eastern Germany, historically part of Lusatia, known in this context as the place where physicist Walther Nernst died.
  • C. Alvier
    Alvier is a prominent mountain peak in the Churfirsten range of the Swiss Alps, known for its scenic hiking routes and panoramic views.
  • D. Vachon
    Vachon is a French-origin surname borne by various notable individuals, including artists, athletes, and public figures.
  • E. Manguin
    Manguin is the surname of Henri Manguin, a French Fauvist painter known for his vibrant use of color and Mediterranean scenes.
  • 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc61f0d808190b1cd2a6ba0d930eb completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78b06c5d081909d31b8a537c94edb completed May 3, 2026, 5:51 p.m.
NEDg Description generation batch_69f78bd727048190a57a75294a9ab53d completed May 3, 2026, 5:54 p.m.
NED2 Entity disambiguation (via description) batch_69f78c94da6c8190b9bc1d04cee19c3c completed May 3, 2026, 5:57 p.m.
Created at: April 9, 2026, 9:52 p.m.