Triple

T4737842
Position Surface form Disambiguated ID Type / Status
Subject John Bold E105167 entity
Predicate relationshipTypeWithSeptimusHarding P10690 FINISHED
Object friend and antagonist 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: friend and antagonist | Statement: [John Bold, relationshipTypeWithSeptimusHarding, friend and antagonist]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithSeptimusHarding
Context triple: [John Bold, relationshipTypeWithSeptimusHarding, friend and antagonist]
  • A. relationshipToHesterPrynne
    Indicates the specific familial, social, or emotional connection that an entity has to Hester Prynne.
  • B. relationshipToRogerChillingworth
    Indicates the specific interpersonal connection or role that one entity has in relation to Roger Chillingworth.
  • C. relationshipWithMiladyDeWinter
    Indicates a personal or interpersonal connection that an entity has with Milady de Winter, such as familial, romantic, adversarial, or other significant relational ties.
  • D. relationshipType chosen
    Indicates the specific kind of relationship that exists between two or more entities.
  • E. relationshipToMissWatson
    Indicates the type or nature of a person's relational connection to Miss Watson (e.g., familial, social, or other defined relationship).
  • 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_69bd43ee52048190b81a4f066534ffb3 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64844b7081909c9d36e4b461379e completed March 20, 2026, 3:15 p.m.
PD Predicate disambiguation batch_69bd6221c3b881908604f35f8de6f16b completed March 20, 2026, 3:05 p.m.
Created at: March 20, 2026, 1:19 p.m.