Triple

T13184056
Position Surface form Disambiguated ID Type / Status
Subject National Indemnity Company E313800 entity
Predicate roleWithinBerkshireHathaway P43130 FINISHED
Object core insurance platform 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: core insurance platform | Statement: [National Indemnity Company, roleWithinBerkshireHathaway, core insurance platform]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: roleWithinBerkshireHathaway
Context triple: [National Indemnity Company, roleWithinBerkshireHathaway, core insurance platform]
  • A. roleWithinBoeing
    Indicates that one entity holds or has held a specific role, position, or function within the organization Boeing.
  • B. roleWithinRaytheon
    Indicates that one entity holds or has held a specific role, position, or function within the organization Raytheon.
  • C. underlyingCompanyRole chosen
    Indicates the specific function, position, or responsibility an entity holds within or in relation to a company.
  • D. hasHeadquartersRoleFor
    Indicates that an entity holds a specific role or position within the headquarters of another entity.
  • E. roleInPaulAllenLegacy
    Indicates that an entity holds or held a specific role or contribution within the legacy, initiatives, or enduring impact associated with Paul Allen.
  • 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_69d806ae1e08819090d95bfe1538cc17 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98cf054f88190b05ced98d5a22a62 completed April 10, 2026, 11:51 p.m.
PD Predicate disambiguation batch_69d98bc2c0c88190be357811aa8e828d completed April 10, 2026, 11:46 p.m.
Created at: April 9, 2026, 9:15 p.m.