Triple

T6458993
Position Surface form Disambiguated ID Type / Status
Subject Jacques-Germain Soufflot E142067 entity
Predicate givenName P17 FINISHED
Object Jacques-Germain
Jacques-Germain was an 18th-century French architect best known for designing the Panthéon in Paris.
E595280 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: Jacques-Germain | Statement: [Jacques-Germain Soufflot, givenName, Jacques-Germain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jacques-Germain
Context triple: [Jacques-Germain Soufflot, givenName, Jacques-Germain]
  • A. Jacques-François
    Jacques-François is the given name of Jacques-François Menou, a French general who served during the French Revolutionary period and in Napoleon’s Egyptian campaign.
  • B. Jacques François
    Jacques François was a French actor known for his supporting roles in mid-20th-century European and American films.
  • C. Jacques-Pierre
    Jacques-Pierre is the given name of Jacques-Pierre Brissot, a prominent French revolutionary leader and journalist during the French Revolution.
  • D. Jean-François
    Jean-François is the given name of Jean-François de La Clue-Sabran, an 18th-century French naval officer and admiral.
  • E. Ange-Jacques
    Ange-Jacques is a French neoclassical architect best known for designing major Parisian landmarks such as the Place de la Concorde and the Petit Trianon at Versailles.
  • 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: Jacques-Germain
Triple: [Jacques-Germain Soufflot, givenName, Jacques-Germain]
Generated description
Jacques-Germain was an 18th-century French architect best known for designing the Panthéon in Paris.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jacques-Germain
Target entity description: Jacques-Germain was an 18th-century French architect best known for designing the Panthéon in Paris.
  • A. Jacques-François
    Jacques-François is the given name of Jacques-François Menou, a French general who served during the French Revolutionary period and in Napoleon’s Egyptian campaign.
  • B. Jacques François
    Jacques François was a French actor known for his supporting roles in mid-20th-century European and American films.
  • C. Jacques-Pierre
    Jacques-Pierre is the given name of Jacques-Pierre Brissot, a prominent French revolutionary leader and journalist during the French Revolution.
  • D. Jean-François
    Jean-François is the given name of Jean-François de La Clue-Sabran, an 18th-century French naval officer and admiral.
  • E. Ange-Jacques
    Ange-Jacques is a French neoclassical architect best known for designing major Parisian landmarks such as the Place de la Concorde and the Petit Trianon at Versailles.
  • 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_69c008d2f91c8190a8178767a35e08fc completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069f347f48190a2b22c5b648b17bd completed March 22, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c653971f988190847187ae60b6eeb5 completed March 27, 2026, 9:53 a.m.
NEDg Description generation batch_69c654907e1081908a322bd8ac03cd88 completed March 27, 2026, 9:57 a.m.
NED2 Entity disambiguation (via description) batch_69c654fafcd88190b28d49e9fe264246 completed March 27, 2026, 9:59 a.m.
Created at: March 22, 2026, 4:48 p.m.