Triple

T494704
Position Surface form Disambiguated ID Type / Status
Subject St Martin E10266 entity
Predicate placeOfDeath P21 FINISHED
Object Candes
Candes is a historic village in central France, best known as the place where Saint Martin of Tours died and now part of the commune Candes-Saint-Martin.
 E61624 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: Candes | Statement: [St Martin, placeOfDeath, Candes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Candes
Context triple: [St Martin, placeOfDeath, Candes]
  • A. Brewster
    Brewster is a coastal town on Cape Cod in Massachusetts known for its scenic beaches, historic charm, and bayside conservation lands.
  • B. Brewster
    Brewster is the given name of Brewster Kahle, an American computer engineer and digital librarian best known as the founder of the Internet Archive.
  • C. Brewster
    Brewster is a small hamlet and census-designated place in Putnam County, New York, known for its historic downtown and role as a local commercial and transportation hub.
  • D. Mariposa
    Mariposa is a small historic town in central California known for its Gold Rush heritage and proximity to Yosemite National Park.
  • E. Luce
    Luce is a surname most notably associated with Henry Luce, the influential American magazine magnate and co-founder of Time Inc.
  • 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: Candes
Triple: [St Martin, placeOfDeath, Candes]
Generated description
Candes is a historic village in central France, best known as the place where Saint Martin of Tours died and now part of the commune Candes-Saint-Martin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Candes
Target entity description: Candes is a historic village in central France, best known as the place where Saint Martin of Tours died and now part of the commune Candes-Saint-Martin.
  • A. Brewster
    Brewster is a coastal town on Cape Cod in Massachusetts known for its scenic beaches, historic charm, and bayside conservation lands.
  • B. Brewster
    Brewster is the given name of Brewster Kahle, an American computer engineer and digital librarian best known as the founder of the Internet Archive.
  • C. Brewster
    Brewster is a small hamlet and census-designated place in Putnam County, New York, known for its historic downtown and role as a local commercial and transportation hub.
  • D. Mariposa
    Mariposa is a small historic town in central California known for its Gold Rush heritage and proximity to Yosemite National Park.
  • E. Luce
    Luce is a surname most notably associated with Henry Luce, the influential American magazine magnate and co-founder of Time Inc.
  • 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_69a2e847df8481909239ec08ccf1e376 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f0fdd5608190815fa36485df8962 completed Feb. 28, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69a47d2da4488190be3146538a4f3d46 completed March 1, 2026, 5:53 p.m.
NEDg Description generation batch_69a47e3bf5e48190b30d2250708e04c6 completed March 1, 2026, 5:58 p.m.
NED2 Entity disambiguation (via description) batch_69a47e888e04819096b3b4eed3bccf95 completed March 1, 2026, 5:59 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.