Triple

T37395062
Position Surface form Disambiguated ID Type / Status
Subject Ecco design team E928827 entity
Predicate parentCompanyOfImprint P15054 FINISHED
Object HarperCollins NE NERFINISHED

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: HarperCollins | Statement: [Ecco design team, parentCompanyOfImprint, HarperCollins]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: parentCompanyOfImprint
Context triple: [Ecco design team, parentCompanyOfImprint, HarperCollins]
  • A. publisherParentCompany chosen
    Indicates that one company serves as the parent (owning or controlling) company of a given publisher.
  • B. ultimateParentCompany
    Indicates that one company is the highest-level controlling entity in a corporate ownership structure, with no parent company above it.
  • C. parentCompanyOfProducer
    Indicates that one company is the parent company that owns or controls a producer entity.
  • D. parentCompanyOfOrigin
    Indicates that one company is the original parent or source company from which another company was created, derived, or spun off.
  • E. parentCompanyInCanon
    Indicates that one company is recognized, within the official canon or continuity of a work, as the parent company of another company.
  • 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_69f76ebb10c481909b54b9dba263e29f completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fe6e492bf8819080b25221d13445ea completed May 8, 2026, 11:14 p.m.
PD Predicate disambiguation batch_69fe6dd33a6881908fe9bbbc184cab51 completed May 8, 2026, 11:12 p.m.
Created at: May 3, 2026, 4:16 p.m.