Triple

T11478225
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Kent E272075 entity
Predicate hasImportantFigure P1183 FINISHED
Object Mellitus E376053 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: Mellitus | Statement: [Kingdom of Kent, hasImportantFigure, Mellitus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mellitus
Context triple: [Kingdom of Kent, hasImportantFigure, Mellitus]
  • A. Mellitus chosen
    Mellitus was an early 7th-century Christian missionary and the first Bishop of London, later serving as Archbishop of Canterbury in Anglo-Saxon England.
  • B. T1D
    T1D is a shorthand name for Terminal 1D, likely referring to a specific passenger terminal section within an airport.
  • C. GDM
    GDM (GNOME Display Manager) is the graphical login and session management system used by the GNOME desktop environment on Unix-like operating systems.
  • D. Diabetes Group
    Diabetes Group is a Medtronic business division focused on developing and providing medical technologies and solutions for diabetes management.
  • E. Hipple
    Hipple is the birth surname of American film and television actor Hugh Marlowe.
  • 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_69d6aae0c8d881908a5a360c0be3242e completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8294e0fe08190b018e840146e27ca completed April 9, 2026, 10:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5e970743c8190a5be4d59d1b941d6 completed April 20, 2026, 8:53 a.m.
Created at: April 8, 2026, 9:36 p.m.