Triple

T16569843
Position Surface form Disambiguated ID Type / Status
Subject Duc de Magenta E402555 entity
Predicate styleOfAddress P536 FINISHED
Object Duc
Duc is a French noble title equivalent to "Duke," historically granted to high-ranking aristocrats and often associated with significant landholdings and political influence.
 E1220809 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: Duc | Statement: [Duc de Magenta, styleOfAddress, Duc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Duc
Context triple: [Duc de Magenta, styleOfAddress, Duc]
  • A. Cuno
    Cuno is a masculine given name of Germanic origin, used in various European countries.
  • B. Ducrot
    Ducrot is a French surname most notably borne by Auguste-Alexandre Ducrot, a 19th-century French general.
  • C. Ercoli
    Ercoli was a pseudonym used by Italian communist leader Palmiro Togliatti, a key figure in 20th-century European leftist politics.
  • D. Luxilus
    Luxilus is a genus of North American freshwater minnows in the family Leuciscidae, commonly found in streams and rivers.
  • E. Conde
    Conde is a coastal municipality in the Brazilian state of Bahia, known for its beaches and location within the Metropolitan Region of Salvador.
  • 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: Duc
Triple: [Duc de Magenta, styleOfAddress, Duc]
Generated description
Duc is a French noble title equivalent to "Duke," historically granted to high-ranking aristocrats and often associated with significant landholdings and political influence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Duc
Target entity description: Duc is a French noble title equivalent to "Duke," historically granted to high-ranking aristocrats and often associated with significant landholdings and political influence.
  • A. Cuno
    Cuno is a masculine given name of Germanic origin, used in various European countries.
  • B. Ducrot
    Ducrot is a French surname most notably borne by Auguste-Alexandre Ducrot, a 19th-century French general.
  • C. Ercoli
    Ercoli was a pseudonym used by Italian communist leader Palmiro Togliatti, a key figure in 20th-century European leftist politics.
  • D. Luxilus
    Luxilus is a genus of North American freshwater minnows in the family Leuciscidae, commonly found in streams and rivers.
  • E. Conde
    Conde is a coastal municipality in the Brazilian state of Bahia, known for its beaches and location within the Metropolitan Region of Salvador.
  • 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_69d8838648088190acf97ef11fc3f61b completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e359580f548190a21afd148bc22d8d completed April 18, 2026, 10:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006ee616a0819089b3cdc1da951735 completed May 10, 2026, 11:41 a.m.
NEDg Description generation batch_6a006f9043b8819086143b2ec0cf1657 completed May 10, 2026, 11:44 a.m.
NED2 Entity disambiguation (via description) batch_6a00701fc1848190b3248a70b462eab1 completed May 10, 2026, 11:46 a.m.
Created at: April 10, 2026, 5:16 a.m.