Triple

T23473960
Position Surface form Disambiguated ID Type / Status
Subject Robert Beugré Mambé E570208 entity
Predicate familyName P18 FINISHED
Object Mambé
Mambé is the surname of Robert Beugré Mambé, an Ivorian politician and public figure.
 E1588328 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: Mambé | Statement: [Robert Beugré Mambé, familyName, Mambé]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mambé
Context triple: [Robert Beugré Mambé, familyName, Mambé]
  • A. Cajiqueño
    Cajiqueño is the Spanish demonym for a person from the Colombian municipality of Cajicá.
  • B. Mitú
    Mitú is a remote Colombian town that serves as the capital of the Vaupés Department in the Amazon rainforest, known for its indigenous communities and dense jungle surroundings.
  • C. Bañuelo
    Bañuelo is a well-preserved 11th-century Arab bathhouse in Granada, Spain, renowned as one of the oldest and best-conserved hammams in the country.
  • D. Kizombo
    Kizombo is a regional dialect of the Kikongo language spoken by Bakongo communities in Central Africa.
  • E. Candanchú
    Candanchú is a historic ski resort in the Spanish Pyrenees, known for its alpine terrain and proximity to the French border.
  • 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: Mambé
Triple: [Robert Beugré Mambé, familyName, Mambé]
Generated description
Mambé is the surname of Robert Beugré Mambé, an Ivorian politician and public figure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mambé
Target entity description: Mambé is the surname of Robert Beugré Mambé, an Ivorian politician and public figure.
  • A. Cajiqueño
    Cajiqueño is the Spanish demonym for a person from the Colombian municipality of Cajicá.
  • B. Mitú
    Mitú is a remote Colombian town that serves as the capital of the Vaupés Department in the Amazon rainforest, known for its indigenous communities and dense jungle surroundings.
  • C. Bañuelo
    Bañuelo is a well-preserved 11th-century Arab bathhouse in Granada, Spain, renowned as one of the oldest and best-conserved hammams in the country.
  • D. Kizombo
    Kizombo is a regional dialect of the Kikongo language spoken by Bakongo communities in Central Africa.
  • E. Candanchú
    Candanchú is a historic ski resort in the Spanish Pyrenees, known for its alpine terrain and proximity to the French border.
  • 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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a70363488190bcbdedec5c2a945c completed April 29, 2026, 6:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c82604cc08190b36c6b9636b6bf42 completed May 19, 2026, 3:31 p.m.
NEDg Description generation batch_6a0ca6f06a348190bfdba0452077f45b completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca7c5176c81908221307bb50ff4ed completed May 19, 2026, 6:11 p.m.
Created at: April 17, 2026, 5:59 p.m.