Triple

T4239368
Position Surface form Disambiguated ID Type / Status
Subject M1026 E94771 entity
Predicate manufacturer P490 FINISHED
Object AM General E21857 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: AM General | Statement: [M1026, manufacturer, AM General]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AM General
Context triple: [M1026, manufacturer, AM General]
  • A. AM General chosen
    AM General is an American heavy vehicle manufacturer best known for developing the military Humvee and its civilian counterpart, the Hummer.
  • B. MAN Truck & Bus
    MAN Truck & Bus is a major European commercial vehicle manufacturer specializing in trucks, buses, and diesel engines, headquartered in Germany and operating worldwide.
  • C. Mack
    Mack is a given name commonly used as a masculine first name or nickname in English-speaking countries.
  • D. GMC
    GMC is the independent regulatory body that oversees medical education and professional standards for doctors in the United Kingdom.
  • E. GMC
    GMC is the commonly used abbreviation for the Great Midwest Conference, a former NCAA collegiate athletic conference in the United States.
  • 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_69b34537cc6481909cd0a96acbb33ef7 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e76b6e0819084d0ce137b5ba74e completed March 12, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a86c95008190b11832c741a11042 completed March 14, 2026, 6:26 p.m.
Created at: March 12, 2026, 11:05 p.m.