Triple

T16179873
Position Surface form Disambiguated ID Type / Status
Subject Morris Garages E392656 entity
Predicate notableModel P1503 FINISHED
Object MG B E392652 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: MG B | Statement: [Morris Garages, notableModel, MG B]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MG B
Context triple: [Morris Garages, notableModel, MG B]
  • A. MG B chosen
    The MG B is a classic British two-seat sports car produced from the early 1960s to 1980, renowned for its simple, lightweight design and enduring popularity among enthusiasts.
  • B. MG A
    The MG A is a classic British two-seat sports car produced by MG in the late 1950s and early 1960s, known for its sleek, modern styling and successful racing pedigree.
  • C. MGB
    MGB was the Soviet Union’s Ministry of State Security, a key secret police and intelligence agency that operated before being reorganized into the KGB.
  • D. MGB
    MGB is a Swiss narrow-gauge railway company operating scenic mountain routes through the Alps, including connections to famous lines like the Glacier Express.
  • E. MGB
    MGB is the Mines and Geosciences Bureau, a Philippine government agency responsible for the conservation, management, and development of the country’s mineral resources and geosciences services.
  • 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e2205b88b481908ecdd8d663dc668b completed April 17, 2026, 11:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a000787d3fc8190a32d53a177fedb6d completed May 10, 2026, 4:20 a.m.
Created at: April 10, 2026, 5:02 a.m.