Triple

T209967
Position Surface form Disambiguated ID Type / Status
Subject Proto-Celtic E4692 entity
Predicate ancestorOf P369 FINISHED
Object Breton
Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
E29282 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: Breton | Statement: [Proto-Celtic, ancestorOf, Breton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Breton
Context triple: [Proto-Celtic, ancestorOf, Breton]
  • A. Brittany
    Brittany is a historic cultural region in northwest France known for its distinct Celtic heritage, Breton language, rugged coastline, and strong Catholic traditions.
  • B. Mor Breizh
    Mor Breizh is the Breton name for the English Channel, the arm of the Atlantic Ocean that separates southern England from northern France.
  • C. Niçard Occitan
    Niçard Occitan is a Romance variety of the Occitan language traditionally spoken in and around the city of Nice in southeastern France.
  • D. Normandy
    Normandy is a historic region in northern France, famous for its medieval duchy, its role in the Norman Conquest of England, and as the site of the D-Day landings in World War II.
  • E. Touraine
    Touraine is a historic region in central France, famed for its Loire Valley châteaux, wine production, and role as a former royal heartland.
  • 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: Breton
Triple: [Proto-Celtic, ancestorOf, Breton]
Generated description
Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Breton
Target entity description: Breton is a Celtic language spoken primarily in Brittany, France, known for its close relation to Cornish and Welsh.
  • A. Brittany
    Brittany is a historic cultural region in northwest France known for its distinct Celtic heritage, Breton language, rugged coastline, and strong Catholic traditions.
  • B. Mor Breizh
    Mor Breizh is the Breton name for the English Channel, the arm of the Atlantic Ocean that separates southern England from northern France.
  • C. Niçard Occitan
    Niçard Occitan is a Romance variety of the Occitan language traditionally spoken in and around the city of Nice in southeastern France.
  • D. Normandy
    Normandy is a historic region in northern France, famous for its medieval duchy, its role in the Norman Conquest of England, and as the site of the D-Day landings in World War II.
  • E. Touraine
    Touraine is a historic region in central France, famed for its Loire Valley châteaux, wine production, and role as a former royal heartland.
  • 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_69a2575cb1dc8190a01ad332426dc339 completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c082fa08190b4d097bf68300222 completed Feb. 28, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69a35b636810819085f6c4e658ee578a completed Feb. 28, 2026, 9:17 p.m.
NEDg Description generation batch_69a35cd77cf881908bbde3b6bcbd5fa8 completed Feb. 28, 2026, 9:23 p.m.
NED2 Entity disambiguation (via description) batch_69a35daaf914819096033b4e95fd3317 completed Feb. 28, 2026, 9:27 p.m.
Created at: Feb. 28, 2026, 2:52 a.m.