Triple

T5246446
Position Surface form Disambiguated ID Type / Status
Subject La Force prison E118470 entity
Predicate hadSection P37078 FINISHED
Object Grande Force
Grande Force was a principal section of Paris’s historic La Force prison, known for holding male prisoners during the Ancien Régime and the French Revolution.
E505344 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: Grande Force | Statement: [La Force prison, hadSection, Grande Force]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grande Force
Context triple: [La Force prison, hadSection, Grande Force]
  • A. Full Force
    Full Force is an American R&B and hip hop production and songwriting group known for crafting hits for artists like Lisa Lisa and Cult Jam, UTFO, and early-career Rihanna.
  • B. Força
    "Força" is a pop song by Nelly Furtado that gained wide recognition as the anthem associated with UEFA Euro 2004.
  • C. Bucksturm
    Bucksturm is a historic medieval tower in Osnabrück, Germany, known for its former use as a city fortification and prison.
  • D. The Mighty
    The Mighty is a 1998 drama film about the friendship between two misfit boys, based on the novel "Freak the Mighty" by Rodman Philbrick.
  • E. L’Assaut
    L’Assaut is a French film best known for featuring actress Rachida Brakni in a prominent role.
  • 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: Grande Force
Triple: [La Force prison, hadSection, Grande Force]
Generated description
Grande Force was a principal section of Paris’s historic La Force prison, known for holding male prisoners during the Ancien Régime and the French Revolution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Grande Force
Target entity description: Grande Force was a principal section of Paris’s historic La Force prison, known for holding male prisoners during the Ancien Régime and the French Revolution.
  • A. Full Force
    Full Force is an American R&B and hip hop production and songwriting group known for crafting hits for artists like Lisa Lisa and Cult Jam, UTFO, and early-career Rihanna.
  • B. Força
    "Força" is a pop song by Nelly Furtado that gained wide recognition as the anthem associated with UEFA Euro 2004.
  • C. Bucksturm
    Bucksturm is a historic medieval tower in Osnabrück, Germany, known for its former use as a city fortification and prison.
  • D. The Mighty
    The Mighty is a 1998 drama film about the friendship between two misfit boys, based on the novel "Freak the Mighty" by Rodman Philbrick.
  • E. L’Assaut
    L’Assaut is a French film best known for featuring actress Rachida Brakni in a prominent role.
  • 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_69bd4468aacc8190a8196f71855cdf4f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b5320748190bcf3be4b6c364f92 completed March 20, 2026, 4:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69bef832ae8481908a90faf66c1db631 completed March 21, 2026, 7:57 p.m.
NEDg Description generation batch_69bef91bb96c819098b7f6bfa578d9ca completed March 21, 2026, 8:01 p.m.
NED2 Entity disambiguation (via description) batch_69bef9dc9c908190aac0f7bcaf427dfc completed March 21, 2026, 8:04 p.m.
Created at: March 20, 2026, 1:50 p.m.