Triple

T14409110
Position Surface form Disambiguated ID Type / Status
Subject Clement VII E357276 entity
Predicate nationality P2 FINISHED
Object Savoyard
A Savoyard is a person from the historical region of Savoy in the western Alps, now divided between France, Italy, and Switzerland.
E271848 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: Savoyard | Statement: [Clement VII, nationality, Savoyard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Savoyard
Context triple: [Clement VII, nationality, Savoyard]
  • A. Guignard
    Guignard was a prominent Brazilian painter and art educator known for his lyrical landscapes and significant influence on modern Brazilian art.
  • B. Savoyard Arpitan
    Savoyard Arpitan is a regional variety of the Arpitan (Franco-Provençal) language traditionally spoken in the Savoy region of the western Alps.
  • C. Seigneux
    Seigneux is a small municipality in the canton of Fribourg in western Switzerland.
  • D. Gave de Pau
    Gave de Pau is a river in southwestern France that flows through the city of Pau and forms part of the Adour river system in the Pyrenees region.
  • E. Montataire
    Montataire is a commune in northern France known for its industrial heritage and proximity to the city of Creil in the Oise department.
  • 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: Savoyard
Triple: [Clement VII, nationality, Savoyard]
Generated description
A Savoyard is a person from the historical region of Savoy in the western Alps, now divided between France, Italy, and Switzerland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Savoyard
Target entity description: A Savoyard is a person from the historical region of Savoy in the western Alps, now divided between France, Italy, and Switzerland.
  • A. Guignard
    Guignard was a prominent Brazilian painter and art educator known for his lyrical landscapes and significant influence on modern Brazilian art.
  • B. Savoyard Arpitan chosen
    Savoyard Arpitan is a regional variety of the Arpitan (Franco-Provençal) language traditionally spoken in the Savoy region of the western Alps.
  • C. Seigneux
    Seigneux is a small municipality in the canton of Fribourg in western Switzerland.
  • D. Gave de Pau
    Gave de Pau is a river in southwestern France that flows through the city of Pau and forms part of the Adour river system in the Pyrenees region.
  • E. Montataire
    Montataire is a commune in northern France known for its industrial heritage and proximity to the city of Creil in the Oise department.
  • F. None of above.

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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90c7a068819081b4b516983a1412 completed April 14, 2026, 7:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5524e26c81909424b5ba88b5f330 completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd56844d7c8190906b6550fb1c28d5 completed May 8, 2026, 3:20 a.m.
NED2 Entity disambiguation (via description) batch_69fd5731c9188190bda2958bef87dfe2 completed May 8, 2026, 3:23 a.m.
Created at: April 10, 2026, 1:17 a.m.