Triple

T23024115
Position Surface form Disambiguated ID Type / Status
Subject Les deux journées E573251 entity
Predicate character P662 FINISHED
Object Mikéli
Mikéli is a fictional character from Alfred de Vigny's historical drama "Les deux journées," set during the turbulent period of the French Revolution.
 E1566451 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: Mikéli | Statement: [Les deux journées, character, Mikéli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mikéli
Context triple: [Les deux journées, character, Mikéli]
  • A. Mikko
    Mikko is a Finnish given name commonly used for males, equivalent to the English name Michael.
  • B. Mik
    Mik is the nickname and given name of Mik Kaminski, the English violinist best known for his work with the rock band Electric Light Orchestra.
  • C. Mik
    Mik is a character associated with Marvel Comics’ Future Foundation, a team of young, highly intelligent heroes connected to the Fantastic Four.
  • D. Milak
    Milak is a border town in India’s Uttar Pradesh state, known as a road-linked crossing point on the route to Afghanistan via Zaranj.
  • E. Michaeli
    Michaeli is a Hebrew-language surname borne by various Israeli public figures, including politicians, academics, and artists.
  • 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: Mikéli
Triple: [Les deux journées, character, Mikéli]
Generated description
Mikéli is a fictional character from Alfred de Vigny's historical drama "Les deux journées," set during the turbulent period of the French Revolution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mikéli
Target entity description: Mikéli is a fictional character from Alfred de Vigny's historical drama "Les deux journées," set during the turbulent period of the French Revolution.
  • A. Mikko
    Mikko is a Finnish given name commonly used for males, equivalent to the English name Michael.
  • B. Mik
    Mik is a character associated with Marvel Comics’ Future Foundation, a team of young, highly intelligent heroes connected to the Fantastic Four.
  • C. Mik
    Mik is the nickname and given name of Mik Kaminski, the English violinist best known for his work with the rock band Electric Light Orchestra.
  • D. Milak
    Milak is a border town in India’s Uttar Pradesh state, known as a road-linked crossing point on the route to Afghanistan via Zaranj.
  • E. Michaeli
    Michaeli is a Hebrew-language surname borne by various Israeli public figures, including politicians, academics, and artists.
  • 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1847b86688190b678d0d09ecd3c3d completed April 29, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2afe2788190844de1fc670d661b completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bfa3b17c88190b5f2d6386f157f72 completed May 19, 2026, 5:50 a.m.
NED2 Entity disambiguation (via description) batch_6a0bfad6a38c8190a77f93dcaab644b7 completed May 19, 2026, 5:53 a.m.
Created at: April 17, 2026, 3:52 p.m.