Triple

T6775471
Position Surface form Disambiguated ID Type / Status
Subject Quimper E155143 entity
Predicate cathedralDedicatedTo P22282 FINISHED
Object Saint Corentin
Saint Corentin is a Breton saint venerated as the first bishop and patron saint of Quimper in Brittany, France.
 E617171 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: Saint Corentin | Statement: [Quimper, cathedralDedicatedTo, Saint Corentin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saint Corentin
Context triple: [Quimper, cathedralDedicatedTo, Saint Corentin]
  • A. Saint Ferréol
    Saint Ferréol is a Christian saint after whom various places and landmarks, such as Lac de Saint-Ferréol in France, are named.
  • B. Saint Africain of Comminges
    Saint Africain of Comminges was a Christian saint and early bishop from the historical region of Comminges in southwestern France, venerated locally and remembered in place names such as the town of Saint-Affrique.
  • C. Grégoire
    Grégoire is the French form of the given name Gregory, commonly used in French-speaking countries.
  • D. Cyrille
    Cyrille is the French given name of early 20th-century Canadian ice hockey star Newsy Lalonde.
  • E. Ambroise
    Ambroise is a modern digital revival of classic Didone-style typefaces, characterized by high contrast between thick and thin strokes and elegant, refined letterforms.
  • 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: Saint Corentin
Triple: [Quimper, cathedralDedicatedTo, Saint Corentin]
Generated description
Saint Corentin is a Breton saint venerated as the first bishop and patron saint of Quimper in Brittany, France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saint Corentin
Target entity description: Saint Corentin is a Breton saint venerated as the first bishop and patron saint of Quimper in Brittany, France.
  • A. Saint Ferréol
    Saint Ferréol is a Christian saint after whom various places and landmarks, such as Lac de Saint-Ferréol in France, are named.
  • B. Saint Africain of Comminges
    Saint Africain of Comminges was a Christian saint and early bishop from the historical region of Comminges in southwestern France, venerated locally and remembered in place names such as the town of Saint-Affrique.
  • C. Grégoire
    Grégoire is the French form of the given name Gregory, commonly used in French-speaking countries.
  • D. Cyrille
    Cyrille is the French given name of early 20th-century Canadian ice hockey star Newsy Lalonde.
  • E. Ambroise
    Ambroise is a modern digital revival of classic Didone-style typefaces, characterized by high contrast between thick and thin strokes and elegant, refined letterforms.
  • 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_69c68812ef7c819099369f51febb725c completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d24f77c88190be21cf4ef132aa31 completed March 27, 2026, 6:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c712ca48d88190b9f47b23264d4264 completed March 27, 2026, 11:29 p.m.
NEDg Description generation batch_69c713d2fad881909ac1b96ba4353bfe completed March 27, 2026, 11:33 p.m.
NED2 Entity disambiguation (via description) batch_69c71478072481909e396a2ac39f0f3a completed March 27, 2026, 11:36 p.m.
Created at: March 27, 2026, 2:13 p.m.