Triple

T18312492
Position Surface form Disambiguated ID Type / Status
Subject Prince Pedro, Duke of Calabria E438661 entity
Predicate child P120 FINISHED
Object Princess Sofía of Bourbon-Two Sicilies
Princess Sofía of Bourbon-Two Sicilies is a member of the Italian branch of the Bourbon royal family, belonging to the historic House of Bourbon-Two Sicilies.
 E1371509 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: Princess Sofía of Bourbon-Two Sicilies | Statement: [Prince Pedro, Duke of Calabria, child, Princess Sofía of Bourbon-Two Sicilies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Princess Sofía of Bourbon-Two Sicilies
Context triple: [Prince Pedro, Duke of Calabria, child, Princess Sofía of Bourbon-Two Sicilies]
  • A. Princess María of Bourbon-Two Sicilies
    Princess María of Bourbon-Two Sicilies was a member of the Italian Bourbon-Two Sicilies royal family and a daughter of the dynasty that once ruled the Kingdom of the Two Sicilies.
  • B. Princess Maria Cristina of Bourbon-Two Sicilies
    Princess Maria Cristina of Bourbon-Two Sicilies was a 19th-century Italian royal, daughter of the last King of the Two Sicilies, known for her role within the exiled Bourbon court after the unification of Italy.
  • C. Princess María de las Mercedes of Bourbon-Two Sicilies
    Princess María de las Mercedes of Bourbon-Two Sicilies was a Spanish noblewoman and member of the House of Bourbon-Two Sicilies who became Countess of Barcelona and the mother of King Juan Carlos I of Spain.
  • D. Princess Maria Cristina of the Two Sicilies
    Princess Maria Cristina of the Two Sicilies was a 19th-century Neapolitan Bourbon princess who became Queen consort of Spain through her marriage to King Ferdinand VII.
  • E. Princess Cristina of Bourbon-Two Sicilies
    Princess Cristina of Bourbon-Two Sicilies is a member of the Italian Bourbon-Two Sicilies royal family, belonging to a cadet branch of the historic House of Bourbon.
  • 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: Princess Sofía of Bourbon-Two Sicilies
Triple: [Prince Pedro, Duke of Calabria, child, Princess Sofía of Bourbon-Two Sicilies]
Generated description
Princess Sofía of Bourbon-Two Sicilies is a member of the Italian branch of the Bourbon royal family, belonging to the historic House of Bourbon-Two Sicilies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Princess Sofía of Bourbon-Two Sicilies
Target entity description: Princess Sofía of Bourbon-Two Sicilies is a member of the Italian branch of the Bourbon royal family, belonging to the historic House of Bourbon-Two Sicilies.
  • A. Princess María of Bourbon-Two Sicilies
    Princess María of Bourbon-Two Sicilies was a member of the Italian Bourbon-Two Sicilies royal family and a daughter of the dynasty that once ruled the Kingdom of the Two Sicilies.
  • B. Princess Maria Cristina of Bourbon-Two Sicilies
    Princess Maria Cristina of Bourbon-Two Sicilies was a 19th-century Italian royal, daughter of the last King of the Two Sicilies, known for her role within the exiled Bourbon court after the unification of Italy.
  • C. Princess María de las Mercedes of Bourbon-Two Sicilies
    Princess María de las Mercedes of Bourbon-Two Sicilies was a Spanish noblewoman and member of the House of Bourbon-Two Sicilies who became Countess of Barcelona and the mother of King Juan Carlos I of Spain.
  • D. Princess Maria Cristina of the Two Sicilies
    Princess Maria Cristina of the Two Sicilies was a 19th-century Neapolitan Bourbon princess who became Queen consort of Spain through her marriage to King Ferdinand VII.
  • E. Princess Cristina of Bourbon-Two Sicilies
    Princess Cristina of Bourbon-Two Sicilies is a member of the Italian Bourbon-Two Sicilies royal family, belonging to a cadet branch of the historic House of Bourbon.
  • 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_69d8b916a2d081909e249e4902f6aad9 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e5021a96b48190976273be3ff3e5c6 completed April 19, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0723f109d48190a70174c9330123cb completed May 15, 2026, 1:47 p.m.
NEDg Description generation batch_6a07251f1fec8190afddb45f3e748a59 completed May 15, 2026, 1:52 p.m.
NED2 Entity disambiguation (via description) batch_6a0725c74ce88190b38c2688b3ad92ee completed May 15, 2026, 1:55 p.m.
Created at: April 10, 2026, 10:36 a.m.