Triple

T3696059
Position Surface form Disambiguated ID Type / Status
Subject Pope Marcellus II E78461 entity
Predicate familyName P18 FINISHED
Object Cervini
Cervini is the Italian noble family from which Pope Marcellus II (Marcello Cervini) originated.
 E380466 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: Cervini | Statement: [Pope Marcellus II, familyName, Cervini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cervini
Context triple: [Pope Marcellus II, familyName, Cervini]
  • A. Gavignano
    Gavignano is a small Italian town in the Lazio region, historically notable as the birthplace of Pope Innocent III.
  • B. Miravalle
    Miravalle is a neighborhood located within the Benito Juárez borough of Mexico City, known for its residential character and urban amenities.
  • C. Caudini
    The Caudini were an ancient Italic people forming one of the principal tribes of the Samnite confederation in southern Italy.
  • D. Borgaretto
    Borgaretto is a locality in northern Italy that hosts industrial facilities, including operations of the aerospace company Avio Aero.
  • E. Valperga
    Valperga is a historical novel by Mary Shelley that reimagines the life and times of the 14th-century Italian warlord Castruccio Castracani through a blend of romance, politics, and philosophical reflection.
  • 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: Cervini
Triple: [Pope Marcellus II, familyName, Cervini]
Generated description
Cervini is the Italian noble family from which Pope Marcellus II (Marcello Cervini) originated.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cervini
Target entity description: Cervini is the Italian noble family from which Pope Marcellus II (Marcello Cervini) originated.
  • A. Gavignano
    Gavignano is a small Italian town in the Lazio region, historically notable as the birthplace of Pope Innocent III.
  • B. Miravalle
    Miravalle is a neighborhood located within the Benito Juárez borough of Mexico City, known for its residential character and urban amenities.
  • C. Caudini
    The Caudini were an ancient Italic people forming one of the principal tribes of the Samnite confederation in southern Italy.
  • D. Borgaretto
    Borgaretto is a locality in northern Italy that hosts industrial facilities, including operations of the aerospace company Avio Aero.
  • E. Valperga
    Valperga is a historical novel by Mary Shelley that reimagines the life and times of the 14th-century Italian warlord Castruccio Castracani through a blend of romance, politics, and philosophical reflection.
  • 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_69ad85e3b1888190abc983e06968696d completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc50f9ad88190a926042fa73d65dc completed March 8, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c3d4821081909ccd1b5789eb761e completed March 14, 2026, 2:11 a.m.
NEDg Description generation batch_69b4c512ea388190839fdcb3711f41a0 completed March 14, 2026, 2:16 a.m.
NED2 Entity disambiguation (via description) batch_69b4c5b4b5848190b799599b8d0a315a completed March 14, 2026, 2:19 a.m.
Created at: March 8, 2026, 3:26 p.m.