Triple

T856479
Position Surface form Disambiguated ID Type / Status
Subject Stéphane Mille E18502 entity
Predicate familyName P18 FINISHED
Object Mille
Mille is a French surname most notably borne by individuals such as Stéphane Mille.
 E107591 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: Mille | Statement: [Stéphane Mille, familyName, Mille]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mille
Context triple: [Stéphane Mille, familyName, Mille]
  • A. Milyan
    Milyan is an extinct Anatolian Indo-European language once spoken in southwestern Asia Minor, known primarily from a small corpus of inscriptions.
  • B. Mila
    Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
  • C. Mvezo
    Mvezo is a small rural village in South Africa’s Eastern Cape best known as the birthplace of Nelson Mandela.
  • D. Munnik
    Munnik is a given name associated with J. B. M. Hertzog, a prominent early 20th-century South African prime minister and political leader.
  • E. Myal
    Myal is an Afro-Caribbean spiritual tradition originating among enslaved Africans in Jamaica, characterized by spirit possession, healing rituals, and resistance to oppression.
  • 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: Mille
Triple: [Stéphane Mille, familyName, Mille]
Generated description
Mille is a French surname most notably borne by individuals such as Stéphane Mille.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mille
Target entity description: Mille is a French surname most notably borne by individuals such as Stéphane Mille.
  • A. Milyan
    Milyan is an extinct Anatolian Indo-European language once spoken in southwestern Asia Minor, known primarily from a small corpus of inscriptions.
  • B. Mila
    Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
  • C. Mvezo
    Mvezo is a small rural village in South Africa’s Eastern Cape best known as the birthplace of Nelson Mandela.
  • D. Munnik
    Munnik is a given name associated with J. B. M. Hertzog, a prominent early 20th-century South African prime minister and political leader.
  • E. Myal
    Myal is an Afro-Caribbean spiritual tradition originating among enslaved Africans in Jamaica, characterized by spirit possession, healing rituals, and resistance to oppression.
  • 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_69a4938bdd3c8190a954a3c11844d9cf completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac3c172481908ed164ee1579ec28 completed March 1, 2026, 9:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c71702fc8190a143fe45b228ae24 completed March 4, 2026, 5:45 a.m.
NEDg Description generation batch_69a7ca67dbc88190b40fd74ad91a4bd6 completed March 4, 2026, 6 a.m.
NED2 Entity disambiguation (via description) batch_69a7cb0b497c8190926fce5cc5e99734 completed March 4, 2026, 6:02 a.m.
Created at: March 1, 2026, 7:39 p.m.