Triple

T6189506
Position Surface form Disambiguated ID Type / Status
Subject Maximus Decimus Meridius E138149 entity
Predicate trainedBy P3665 FINISHED
Object Proximo
Proximo is the former gladiator-turned-lanista in the film "Gladiator" who owns and mentors Maximus in the arena.
 E574698 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: Proximo | Statement: [Maximus Decimus Meridius, trainedBy, Proximo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Proximo
Context triple: [Maximus Decimus Meridius, trainedBy, Proximo]
  • A. Nexo
    Nexo is a town on the eastern coast of the Danish island of Bornholm, known for its fishing harbor and coastal scenery.
  • B. Avant
    Avant is an American R&B singer and songwriter known for smooth, soulful ballads and early-2000s hits like "Separated" and "Read Your Mind."
  • C. Neox
    Neox is a Spanish television channel owned by Atresmedia that primarily targets young audiences with a mix of series, films, and entertainment programs.
  • D. Nova
    Nova is the name given to TransPennine Express’s modern fleet of intercity trains used across its key routes in the North of England and Scotland.
  • E. Nova
    Nova is a Spanish television channel that primarily targets female audiences with a mix of telenovelas, lifestyle programs, and entertainment content.
  • 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: Proximo
Triple: [Maximus Decimus Meridius, trainedBy, Proximo]
Generated description
Proximo is the former gladiator-turned-lanista in the film "Gladiator" who owns and mentors Maximus in the arena.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Proximo
Target entity description: Proximo is the former gladiator-turned-lanista in the film "Gladiator" who owns and mentors Maximus in the arena.
  • A. Nexo
    Nexo is a town on the eastern coast of the Danish island of Bornholm, known for its fishing harbor and coastal scenery.
  • B. Avant
    Avant is an American R&B singer and songwriter known for smooth, soulful ballads and early-2000s hits like "Separated" and "Read Your Mind."
  • C. Neox
    Neox is a Spanish television channel owned by Atresmedia that primarily targets young audiences with a mix of series, films, and entertainment programs.
  • D. Nova
    Nova is the name given to TransPennine Express’s modern fleet of intercity trains used across its key routes in the North of England and Scotland.
  • E. Nova
    Nova is a Spanish television channel that primarily targets female audiences with a mix of telenovelas, lifestyle programs, and entertainment content.
  • 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062192c5481909eb41f8c5d1208a3 completed March 22, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16f06c770819087e055cfe6c8b134 completed March 23, 2026, 4:49 p.m.
NEDg Description generation batch_69c1bfb484ac8190903efdf4a18f3a1c completed March 23, 2026, 10:33 p.m.
NED2 Entity disambiguation (via description) batch_69c1c03551008190af5e3427b4cdcd11 completed March 23, 2026, 10:35 p.m.
Created at: March 22, 2026, 4:19 p.m.