Triple

T6612008
Position Surface form Disambiguated ID Type / Status
Subject Sir Jackie Stewart E149257 entity
Predicate racedForTeam P60038 FINISHED
Object BRM
BRM (British Racing Motors) was a British Formula One constructor and team known for competing in the World Championship from the 1950s to the 1970s and winning the 1962 Constructors' title.
 E601550 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: BRM | Statement: [Sir Jackie Stewart, racedForTeam, BRM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BRM
Context triple: [Sir Jackie Stewart, racedForTeam, BRM]
  • A. BNRM
    BNRM is the National Library of the Kingdom of Morocco, serving as the country’s main institution for preserving and providing access to its written and documentary heritage.
  • B. BRMB
    BRMB is the commonly used abbreviation for the Big Red Marching Band, the marching band of Cornell University.
  • C. BRS
    BRS is the IATA airport code for Bristol Airport, a major regional airport serving Bristol and the southwest of England.
  • D. BRS
    BRS is the acronym commonly used for Biotechnology Regulatory Services, a U.S. regulatory program overseeing the safe development and use of certain genetically engineered organisms.
  • E. BRL
    BRL is the official currency code for the Brazilian real, the legal tender of Brazil.
  • 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: BRM
Triple: [Sir Jackie Stewart, racedForTeam, BRM]
Generated description
BRM (British Racing Motors) was a British Formula One constructor and team known for competing in the World Championship from the 1950s to the 1970s and winning the 1962 Constructors' title.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BRM
Target entity description: BRM (British Racing Motors) was a British Formula One constructor and team known for competing in the World Championship from the 1950s to the 1970s and winning the 1962 Constructors' title.
  • A. BNRM
    BNRM is the National Library of the Kingdom of Morocco, serving as the country’s main institution for preserving and providing access to its written and documentary heritage.
  • B. BRMB
    BRMB is the commonly used abbreviation for the Big Red Marching Band, the marching band of Cornell University.
  • C. BRS
    BRS is the IATA airport code for Bristol Airport, a major regional airport serving Bristol and the southwest of England.
  • D. BRS
    BRS is the acronym commonly used for Biotechnology Regulatory Services, a U.S. regulatory program overseeing the safe development and use of certain genetically engineered organisms.
  • E. BRL
    BRL is the official currency code for the Brazilian real, the legal tender of Brazil.
  • 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_69c687ebc680819094caf71faba2efe2 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6af3778a8819094e83afed7c6596f completed March 27, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cbd651c08190a19513645fc781c9 completed March 27, 2026, 6:26 p.m.
NEDg Description generation batch_69c6cd88f66c81909b364a816aeee8bf completed March 27, 2026, 6:33 p.m.
NED2 Entity disambiguation (via description) batch_69c6ce3a53cc8190a40d696a22ec65f4 completed March 27, 2026, 6:36 p.m.
Created at: March 27, 2026, 1:57 p.m.