Triple

T9384456
Position Surface form Disambiguated ID Type / Status
Subject Andrea Doria E225869 entity
Predicate familyName P18 FINISHED
Object Doria
Doria is an influential Genoese noble family historically prominent in maritime, political, and military affairs of the Republic of Genoa.
 E796771 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: Doria | Statement: [Andrea Doria, familyName, Doria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Doria
Context triple: [Andrea Doria, familyName, Doria]
  • A. Barbarigo
    Barbarigo is an Italian noble family name historically associated with prominent Venetian statesmen and doges.
  • B. Iolanda
    Iolanda is a feminine given name, a variant of Yolanda, used in various European languages.
  • C. Medina Sidonia
    Medina Sidonia was a Spanish nobleman and admiral best known for commanding the Spanish Armada during its ill-fated 1588 campaign against England.
  • D. Maddalena
    Maddalena is the Italian form of the given name Magdalena, traditionally associated with Mary Magdalene in Christian tradition.
  • E. Rosanero
    Rosanero is the traditional nickname of Italian football club Palermo FC, referring to the club’s distinctive pink-and-black colors.
  • 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: Doria
Triple: [Andrea Doria, familyName, Doria]
Generated description
Doria is an influential Genoese noble family historically prominent in maritime, political, and military affairs of the Republic of Genoa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Doria
Target entity description: Doria is an influential Genoese noble family historically prominent in maritime, political, and military affairs of the Republic of Genoa.
  • A. Barbarigo
    Barbarigo is an Italian noble family name historically associated with prominent Venetian statesmen and doges.
  • B. Iolanda
    Iolanda is a feminine given name, a variant of Yolanda, used in various European languages.
  • C. Medina Sidonia
    Medina Sidonia was a Spanish nobleman and admiral best known for commanding the Spanish Armada during its ill-fated 1588 campaign against England.
  • D. Maddalena
    Maddalena is the Italian form of the given name Magdalena, traditionally associated with Mary Magdalene in Christian tradition.
  • E. Rosanero
    Rosanero is the traditional nickname of Italian football club Palermo FC, referring to the club’s distinctive pink-and-black colors.
  • 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_69ca842e9dcc8190a264119e683cfe04 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd50c23e7881908112597a1771afa5 completed April 1, 2026, 5:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69d100e4fff08190abb4865004462841 completed April 4, 2026, 12:15 p.m.
NEDg Description generation batch_69d10430eec481908e06dd1f6bd12020 completed April 4, 2026, 12:29 p.m.
NED2 Entity disambiguation (via description) batch_69d104a6fb4481908a27f72e3f2d1811 completed April 4, 2026, 12:31 p.m.
Created at: March 30, 2026, 7:44 p.m.