Triple

T9790762
Position Surface form Disambiguated ID Type / Status
Subject Cummins E237599 entity
Predicate tickerSymbol P1447 FINISHED
Object CMI
CMI is the stock ticker symbol for Cummins Inc., a major American manufacturer of engines, power systems, and related technologies.
 E821897 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: CMI | Statement: [Cummins, tickerSymbol, CMI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CMI
Context triple: [Cummins, tickerSymbol, CMI]
  • A. CMI
    CMI is the three-letter IATA airport code for University of Illinois Willard Airport, serving the Champaign–Urbana area in Illinois, USA.
  • B. NCMI
    NCMI is a U.S. Defense Department intelligence organization that collects and analyzes global medical and health-related information to support military and national security decision-making.
  • C. CAMI
    CAMI is the abbreviated name for the Council of Arab Ministers of Interior, a regional body coordinating interior and security policies among Arab states.
  • D. CSM
    CSM is the Italian High Council of the Judiciary, the constitutional body that oversees the independence, careers, and discipline of judges and public prosecutors in Italy.
  • E. CSM
    CSM is a renowned London art and design college known for its influential fashion, fine art, and creative industries programs.
  • 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: CMI
Triple: [Cummins, tickerSymbol, CMI]
Generated description
CMI is the stock ticker symbol for Cummins Inc., a major American manufacturer of engines, power systems, and related technologies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CMI
Target entity description: CMI is the stock ticker symbol for Cummins Inc., a major American manufacturer of engines, power systems, and related technologies.
  • A. CMI
    CMI is the three-letter IATA airport code for University of Illinois Willard Airport, serving the Champaign–Urbana area in Illinois, USA.
  • B. NCMI
    NCMI is a U.S. Defense Department intelligence organization that collects and analyzes global medical and health-related information to support military and national security decision-making.
  • C. CAMI
    CAMI is the abbreviated name for the Council of Arab Ministers of Interior, a regional body coordinating interior and security policies among Arab states.
  • D. CSM
    CSM is the Italian High Council of the Judiciary, the constitutional body that oversees the independence, careers, and discipline of judges and public prosecutors in Italy.
  • E. CSM
    CSM is a renowned London art and design college known for its influential fashion, fine art, and creative industries programs.
  • 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_69ca84dc04488190b9c91193976c0960 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda215b3108190a897552e1dc91cc4 completed April 1, 2026, 10:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c43141cc81908c45a3f5d5103564 completed April 5, 2026, 2:08 a.m.
NEDg Description generation batch_69d1c4b07cec8190a2e6c49efad3a841 completed April 5, 2026, 2:10 a.m.
NED2 Entity disambiguation (via description) batch_69d1c547a9808190b96face03c4203b0 completed April 5, 2026, 2:13 a.m.
Created at: March 30, 2026, 8:28 p.m.