Triple

T5883609
Position Surface form Disambiguated ID Type / Status
Subject Didone typefaces E130806 entity
Predicate hasSubtype P1244 FINISHED
Object Ambroise
Ambroise is a modern digital revival of classic Didone-style typefaces, characterized by high contrast between thick and thin strokes and elegant, refined letterforms.
 E566884 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: Ambroise | Statement: [Didone typefaces, hasSubtype, Ambroise]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ambroise
Context triple: [Didone typefaces, hasSubtype, Ambroise]
  • A. Firmin
    Firmin is a French given name notably borne by Firmin Didot, a renowned printer, typefounder, and member of the influential Didot family in the history of typography.
  • B. Grégoire
    Grégoire is the French form of the given name Gregory, commonly used in French-speaking countries.
  • C. Étienne
    Étienne is the given first name of the French Symbolist poet Stéphane Mallarmé.
  • D. Ambroise Dupont
    Ambroise Dupont was a 19th-century French publisher known for issuing works such as Émile Zola’s novel "Thérèse Raquin."
  • E. Gilles-Barnabé
    Gilles-Barnabé is the given name of Gilles-Barnabé Guimard, an individual identifiable primarily through this personal name.
  • 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: Ambroise
Triple: [Didone typefaces, hasSubtype, Ambroise]
Generated description
Ambroise is a modern digital revival of classic Didone-style typefaces, characterized by high contrast between thick and thin strokes and elegant, refined letterforms.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ambroise
Target entity description: Ambroise is a modern digital revival of classic Didone-style typefaces, characterized by high contrast between thick and thin strokes and elegant, refined letterforms.
  • A. Firmin
    Firmin is a French given name notably borne by Firmin Didot, a renowned printer, typefounder, and member of the influential Didot family in the history of typography.
  • B. Grégoire
    Grégoire is the French form of the given name Gregory, commonly used in French-speaking countries.
  • C. Étienne
    Étienne is the given first name of the French Symbolist poet Stéphane Mallarmé.
  • D. Ambroise Dupont
    Ambroise Dupont was a 19th-century French publisher known for issuing works such as Émile Zola’s novel "Thérèse Raquin."
  • E. Gilles-Barnabé
    Gilles-Barnabé is the given name of Gilles-Barnabé Guimard, an individual identifiable primarily through this personal name.
  • 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_69c0085628dc8190b334c1b44c067efc completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03675747c81908936405c27c2719b completed March 22, 2026, 6:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11cbc676c8190bdac874391a608e8 completed March 23, 2026, 10:58 a.m.
NEDg Description generation batch_69c11d9102648190a61e9a85ead0fff4 completed March 23, 2026, 11:01 a.m.
NED2 Entity disambiguation (via description) batch_69c11e76f5c48190adabb10472729cb2 completed March 23, 2026, 11:05 a.m.
Created at: March 22, 2026, 3:57 p.m.