Triple

T13657480
Position Surface form Disambiguated ID Type / Status
Subject Marquis E326898 entity
Predicate correspondsToTitleInBritain P70523 FINISHED
Object Marquess LITERAL 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: Marquess | Statement: [Marquis, correspondsToTitleInBritain, Marquess]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: correspondsToTitleInBritain
Context triple: [Marquis, correspondsToTitleInBritain, Marquess]
  • A. equivalentTitleInUnitedKingdom chosen
    Indicates that one entity has a title that is considered the equivalent of another entity’s title specifically within the context of the United Kingdom.
  • B. equivalentTitleInEngland
    Indicates that one title corresponds to an equivalent or matching title within the context of England’s system of titles.
  • C. broadcastInUnitedKingdomBy
    Indicates that something (such as a program or event) is or was broadcast by a particular broadcaster within the United Kingdom.
  • D. UKTitle
    Indicates that an entity holds a specific title or name as used in the United Kingdom context.
  • E. locatedInBritishCountry
    Indicates that one entity is geographically or administratively situated within a country that is part of the United Kingdom.
  • F. None of above.

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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc61d56e4819084ae3c16ecdf4a05 completed April 12, 2026, 4:19 p.m.
PD Predicate disambiguation batch_69dbbe8a027081908d8f884b89707a5e completed April 12, 2026, 3:47 p.m.
Created at: April 9, 2026, 9:52 p.m.