Triple

T3925353
Position Surface form Disambiguated ID Type / Status
Subject Areva E93261 entity
Predicate formedByMergerOf P77 FINISHED
Object Cogema
Cogema was a major French nuclear fuel cycle company that specialized in uranium mining, fuel fabrication, and reprocessing before becoming part of Areva.
 E400395 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: Cogema | Statement: [Areva, formedByMergerOf, Cogema]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cogema
Context triple: [Areva, formedByMergerOf, Cogema]
  • A. Clementina
    Clementina is a feminine given name, often considered a variant of Clementine, used in various European and Latin American cultures.
  • B. Paola
    Paola is an Italian noblewoman who became Queen consort of Belgium as the wife of King Albert II.
  • C. Paola
    Paola is a town in southeastern Malta known for its historic sites, including the prehistoric Ħal Saflieni Hypogeum and other cultural landmarks.
  • D. Amada
    Amada is an ancient Egyptian temple site in Lower Nubia, renowned for its well-preserved reliefs and inscriptions dating back to the 18th Dynasty.
  • E. Romina
    Romina is an Italian-American actress and singer best known as half of the pop duo Al Bano & Romina Power.
  • 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: Cogema
Triple: [Areva, formedByMergerOf, Cogema]
Generated description
Cogema was a major French nuclear fuel cycle company that specialized in uranium mining, fuel fabrication, and reprocessing before becoming part of Areva.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cogema
Target entity description: Cogema was a major French nuclear fuel cycle company that specialized in uranium mining, fuel fabrication, and reprocessing before becoming part of Areva.
  • A. Clementina
    Clementina is a feminine given name, often considered a variant of Clementine, used in various European and Latin American cultures.
  • B. Paola
    Paola is an Italian noblewoman who became Queen consort of Belgium as the wife of King Albert II.
  • C. Paola
    Paola is a town in southeastern Malta known for its historic sites, including the prehistoric Ħal Saflieni Hypogeum and other cultural landmarks.
  • D. Amada
    Amada is an ancient Egyptian temple site in Lower Nubia, renowned for its well-preserved reliefs and inscriptions dating back to the 18th Dynasty.
  • E. Romina
    Romina is an Italian-American actress and singer best known as half of the pop duo Al Bano & Romina Power.
  • 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_69aed96bfa1081908f7b30f2c647dee6 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeed7f3cc881909464db1970ba39ae completed March 9, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b52873d5a881909c4c29f06b94a467 completed March 14, 2026, 9:20 a.m.
NEDg Description generation batch_69b52c7951d881908a3111581e0ab511 completed March 14, 2026, 9:38 a.m.
NED2 Entity disambiguation (via description) batch_69b52cd24e988190b25e3b3ccc937fdd completed March 14, 2026, 9:39 a.m.
Created at: March 9, 2026, 3:23 p.m.