Triple

T6930049
Position Surface form Disambiguated ID Type / Status
Subject Roman E160408 entity
Predicate hasCognate P2525 FINISHED
Object Romain
Romain is a French given name and surname derived from the Latin name Romanus, commonly used in Francophone countries.
 E628910 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: Romain | Statement: [Roman, hasCognate, Romain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Romain
Context triple: [Roman, hasCognate, Romain]
  • A. Clément
    Clément is a French given name, equivalent to Clement in English, commonly used for males.
  • B. Valère
    Valère is a character in Molière’s comedy "Tartuffe," known as Mariane’s suitor and a foil to the hypocrisy embodied by Tartuffe.
  • C. Valère
    Valère is a young nobleman in Molière’s comedy *L’Avare*, known for his secret love for Harpagon’s daughter Élise and his role in opposing the miserly values of her father.
  • D. Cyrille
    Cyrille is the French given name of early 20th-century Canadian ice hockey star Newsy Lalonde.
  • E. Maxence
    Maxence is a given name of French origin, used as a variant of the name Max.
  • 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: Romain
Triple: [Roman, hasCognate, Romain]
Generated description
Romain is a French given name and surname derived from the Latin name Romanus, commonly used in Francophone countries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Romain
Target entity description: Romain is a French given name and surname derived from the Latin name Romanus, commonly used in Francophone countries.
  • A. Clément
    Clément is a French given name, equivalent to Clement in English, commonly used for males.
  • B. Valère
    Valère is a character in Molière’s comedy "Tartuffe," known as Mariane’s suitor and a foil to the hypocrisy embodied by Tartuffe.
  • C. Valère
    Valère is a young nobleman in Molière’s comedy *L’Avare*, known for his secret love for Harpagon’s daughter Élise and his role in opposing the miserly values of her father.
  • D. Cyrille
    Cyrille is the French given name of early 20th-century Canadian ice hockey star Newsy Lalonde.
  • E. Maxence
    Maxence is a given name of French origin, used as a variant of the name Max.
  • 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_69c6884e15208190b9e91487eaafcf85 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da1f5fcc8190b43f53f90fc1821c completed March 27, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7514774d88190af212d7953014703 completed March 28, 2026, 3:55 a.m.
NEDg Description generation batch_69c7524d677c81909531ba9bb46f2632 completed March 28, 2026, 4 a.m.
NED2 Entity disambiguation (via description) batch_69c752bef2808190843f3cad53aa5702 completed March 28, 2026, 4:02 a.m.
Created at: March 27, 2026, 2:27 p.m.