Triple

T7796544
Position Surface form Disambiguated ID Type / Status
Subject AU Assembly E180311 entity
Predicate scope P36 FINISHED
Object Continental E95172 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: Continental | Statement: [AU Assembly, scope, Continental]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Continental
Context triple: [AU Assembly, scope, Continental]
  • A. Continental chosen
    Continental is a major German automotive manufacturing company best known for producing tires, braking systems, and other vehicle components.
  • B. The Continental
    The Continental is a television series set in the John Wick universe that explores the origins and inner workings of the assassin-run hotel chain.
  • C. The Continental
    The Continental is a famous dance song that became widely known through its featured performance in the 1934 musical film "The Gay Divorcee."
  • D. CONTINENTAL
    CONTINENTAL is the radio callsign historically used by Continental Airlines for air traffic control communications.
  • E. Continental Mark VI
    The Continental Mark VI is a full-size personal luxury coupe and sedan produced by Lincoln in the early 1980s as part of its long-running Mark series.
  • 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_69ca827d22208190b4dc5aa680edcf5d completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cae94c41408190b73e37c0ff2c6628 completed March 30, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb13f866ac8190bca2b8477b62d7e4 completed March 31, 2026, 12:23 a.m.
Created at: March 30, 2026, 4:32 p.m.