Triple

T3827431
Position Surface form Disambiguated ID Type / Status
Subject Marvejols E88723 entity
Predicate historicalRegion P915 FINISHED
Object Gevaudan
Gevaudan is a historic region in south-central France, best known for the 18th-century legend of the Beast of Gévaudan that terrorized its countryside.
 E391426 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: Gevaudan | Statement: [Marvejols, historicalRegion, Gevaudan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gevaudan
Context triple: [Marvejols, historicalRegion, Gevaudan]
  • A. Moreau
    Moreau is a town in Saratoga County, New York, known for its residential communities and proximity to natural and recreational areas such as Moreau Lake State Park.
  • B. Moreau
    Moreau is a French surname most famously associated with the 19th-century Symbolist painter Gustave Moreau.
  • C. Gaspard
    Gaspard is a French masculine given name historically borne by notable figures such as nobles, military leaders, and artists.
  • D. Villani
    Villani is the surname of Cédric Villani, a renowned French mathematician and Fields Medal laureate known for his work in partial differential equations and mathematical physics.
  • E. Savini
    Savini is an Italian surname most famously associated with Tom Savini, a renowned special effects and makeup artist in horror cinema.
  • 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: Gevaudan
Triple: [Marvejols, historicalRegion, Gevaudan]
Generated description
Gevaudan is a historic region in south-central France, best known for the 18th-century legend of the Beast of Gévaudan that terrorized its countryside.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gevaudan
Target entity description: Gevaudan is a historic region in south-central France, best known for the 18th-century legend of the Beast of Gévaudan that terrorized its countryside.
  • A. Moreau
    Moreau is a town in Saratoga County, New York, known for its residential communities and proximity to natural and recreational areas such as Moreau Lake State Park.
  • B. Moreau
    Moreau is a French surname most famously associated with the 19th-century Symbolist painter Gustave Moreau.
  • C. Gaspard
    Gaspard is a French masculine given name historically borne by notable figures such as nobles, military leaders, and artists.
  • D. Villani
    Villani is the surname of Cédric Villani, a renowned French mathematician and Fields Medal laureate known for his work in partial differential equations and mathematical physics.
  • E. Savini
    Savini is an Italian surname most famously associated with Tom Savini, a renowned special effects and makeup artist in horror cinema.
  • 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_69aed9538cf881909d9ce8ca4ac7c18c completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeeb66c0bc819084d9a9fe32e8433a completed March 9, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb51e6248190b242f9e498a320d3 completed March 14, 2026, 6:08 a.m.
NEDg Description generation batch_69b4fbc972ec81908fb0d53e851236c4 completed March 14, 2026, 6:10 a.m.
NED2 Entity disambiguation (via description) batch_69b4ffd256c08190a0cfee3bd0dafda3 completed March 14, 2026, 6:27 a.m.
Created at: March 9, 2026, 3:17 p.m.