Triple

T14330116
Position Surface form Disambiguated ID Type / Status
Subject Ultium Cells E355322 entity
Predicate servesBrand P6337 FINISHED
Object Cadillac E11890 NE FINISHED

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: Cadillac | Statement: [Ultium Cells, servesBrand, Cadillac]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cadillac
Context triple: [Ultium Cells, servesBrand, Cadillac]
  • A. Cadillac chosen
    Cadillac is a luxury automobile brand known for its premium vehicles and long-standing association with American upscale motoring.
  • B. Cadillac
    Cadillac is a small city in northern Michigan known for its surrounding lakes, outdoor recreation, and role as a regional tourism and service hub.
  • C. Cadillac
    Cadillac is a Montreal Metro station on the Green Line serving the Mercier–Hochelaga-Maisonneuve borough in Montreal, Quebec, Canada.
  • D. Buick
    Buick is an American automobile marque known for producing upscale, comfort-oriented vehicles positioned between mainstream and luxury brands.
  • E. Cadillac Calais
    The Cadillac Calais was a full-size luxury car produced by Cadillac from the mid-1960s to the mid-1970s, positioned as the brand’s entry-level model during that era.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c1def0081908f03cda8e84d20c0 completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bbb672c8190b25f7046500c56e2 completed May 8, 2026, 3:42 a.m.
Created at: April 10, 2026, 1:13 a.m.