Triple

T25756112
Position Surface form Disambiguated ID Type / Status
Subject Delmarva Power E648600 entity
Predicate hasCustomerPrograms P171734 FINISHED
Object energy efficiency programs 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: energy efficiency programs | Statement: [Delmarva Power, hasCustomerPrograms, energy efficiency programs]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasCustomerPrograms
Context triple: [Delmarva Power, hasCustomerPrograms, energy efficiency programs]
  • A. hasAwardProgram
    Indicates that an entity maintains or offers a formal award or recognition program.
  • B. hasMembershipProgram
    Indicates that an entity offers or participates in a structured membership program, typically providing special access, benefits, or services to enrolled members.
  • C. hasCoopPrograms
    Indicates that an entity offers or participates in cooperative education programs in partnership with other organizations or institutions.
  • D. hasPartnershipProgram
    Indicates that an entity maintains a formal partnership program through which it establishes and manages collaborative relationships with other entities.
  • E. offersProgramsIn
    Indicates that an institution or provider makes educational or training programs available in a particular field, subject, or area.
  • F. None of above. chosen

Provenance (4 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_69e7ab314d788190b3abe19e114080e1 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f6a28c7c148190bfc980aad9f678ca completed May 3, 2026, 1:19 a.m.
PD Predicate disambiguation batch_69f69fe1e3c88190830bb2e9f407357e completed May 3, 2026, 1:07 a.m.
PDg Predicate description generation batch_69f6a28b8ea881908733485374771c51 completed May 3, 2026, 1:19 a.m.
Created at: April 22, 2026, 4:40 a.m.