Triple

T18569808
Position Surface form Disambiguated ID Type / Status
Subject Pat Cummins E453845 entity
Predicate familyName P18 FINISHED
Object Cummins NE NERFINISHED

How this triple was built (2 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: Cummins | Statement: [Pat Cummins, familyName, Cummins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cummins
Context triple: [Pat Cummins, familyName, Cummins]
  • A. Cummins chosen
    Cummins is a global power technology company best known for designing, manufacturing, and servicing diesel and alternative-fuel engines and related power systems.
  • B. Cummins Unit
    Cummins Unit is a large state prison farm in Arkansas known for housing adult male inmates and operating extensive agricultural and industrial programs.
  • C. Perkins Engines Company Limited
    Perkins Engines Company Limited is a British manufacturer renowned for its diesel engines used in industrial, agricultural, construction, and power generation applications worldwide.
  • D. Cummins ISX engines
    Cummins ISX engines are a family of heavy-duty diesel engines widely used in commercial trucks and known for their power, durability, and fuel efficiency.
  • E. PACCAR
    PACCAR is a major American manufacturer of commercial trucks and related heavy-duty vehicles headquartered in Bellevue, Washington.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53b01331c8190bec3aba40358a843 completed April 19, 2026, 8:28 p.m.
Created at: April 10, 2026, 11:43 a.m.