Triple

T2214586
Position Surface form Disambiguated ID Type / Status
Subject Conservatoire de Paris E47995 entity
Predicate shortName P43 FINISHED
Object CNSMDP
CNSMDP is the acronym for the Conservatoire de Paris, France’s premier higher education institution for music and dance.
 E243937 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: CNSMDP | Statement: [Conservatoire de Paris, shortName, CNSMDP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CNSMDP
Context triple: [Conservatoire de Paris, shortName, CNSMDP]
  • A. MDP
    MDP is the stock ticker symbol for Meredith Corporation, a former American media and marketing company known for its magazine publishing and broadcasting operations.
  • B. CPS
    CPS is the principal public agency in England and Wales responsible for prosecuting criminal cases investigated by the police.
  • C. MPC
    MPC is the commonly used abbreviation for the Monetary Policy Committee, the body responsible for setting key interest rates and guiding monetary policy in several countries, including the United Kingdom.
  • D. MCPOCG
    MCPOCG is the highest senior enlisted rank and principal enlisted advisor to the Commandant in the United States Coast Guard.
  • E. Monte Carlo tree search
    Monte Carlo tree search is a heuristic search algorithm that uses random sampling of game states to build and explore a search tree, enabling strong decision-making in complex domains like Go and other board games.
  • 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: CNSMDP
Triple: [Conservatoire de Paris, shortName, CNSMDP]
Generated description
CNSMDP is the acronym for the Conservatoire de Paris, France’s premier higher education institution for music and dance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CNSMDP
Target entity description: CNSMDP is the acronym for the Conservatoire de Paris, France’s premier higher education institution for music and dance.
  • A. MDP
    MDP is the stock ticker symbol for Meredith Corporation, a former American media and marketing company known for its magazine publishing and broadcasting operations.
  • B. CPS
    CPS is the principal public agency in England and Wales responsible for prosecuting criminal cases investigated by the police.
  • C. MPC
    MPC is the commonly used abbreviation for the Monetary Policy Committee, the body responsible for setting key interest rates and guiding monetary policy in several countries, including the United Kingdom.
  • D. MCPOCG
    MCPOCG is the highest senior enlisted rank and principal enlisted advisor to the Commandant in the United States Coast Guard.
  • E. Monte Carlo tree search
    Monte Carlo tree search is a heuristic search algorithm that uses random sampling of game states to build and explore a search tree, enabling strong decision-making in complex domains like Go and other board games.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbfef875c8190b642736b4cc11d4c completed March 7, 2026, 6:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6554f3308190a180cac3ad7e2ce4 completed March 9, 2026, 6:14 a.m.
NEDg Description generation batch_69ae65d419048190ad723d21ab7f1cab completed March 9, 2026, 6:16 a.m.
NED2 Entity disambiguation (via description) batch_69ae666e71908190b50be2cac5bdfa28 completed March 9, 2026, 6:19 a.m.
Created at: March 4, 2026, 7:46 p.m.