Triple

T889171
Position Surface form Disambiguated ID Type / Status
Subject Maryland General Assembly E19199 entity
Predicate hasAbbreviation P43 FINISHED
Object MGA E19199 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: MGA | Statement: [Maryland General Assembly, hasAbbreviation, MGA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MGA
Context triple: [Maryland General Assembly, hasAbbreviation, MGA]
  • A. MGA chosen
    MGA is the commonly used abbreviation for the Maryland General Assembly, the state’s bicameral legislative body.
  • B. MG
    MG is a historic British automotive marque best known for its sports cars, now owned and produced by Chinese manufacturer SAIC Motor.
  • C. MGM
    MGM (Metro-Goldwyn-Mayer) is a historic American film studio renowned for its iconic roaring lion logo and for producing many of the most famous movies of Hollywood’s Golden Age.
  • D. MICA Entertainment
    MICA Entertainment is a film production company known for helping finance and produce feature films such as the historical adventure drama "The Lost City of Z."
  • E. MAG
    MAG is a major British airport operator that owns and manages several UK airports, including Manchester Airport.
  • 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_69a4939d37188190848be3d426ebc9ae completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4acff52008190ac2975c08ad29f54 completed March 1, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c023464481909759c457e87266ab completed March 4, 2026, 5:16 a.m.
Created at: March 1, 2026, 7:39 p.m.