Triple

T36750673
Position Surface form Disambiguated ID Type / Status
Subject ZL E907902 entity
Predicate codeAuthority P135938 FINISHED
Object Dutch railway operators 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: Dutch railway operators | Statement: [ZL, codeAuthority, Dutch railway operators]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: codeAuthority
Context triple: [ZL, codeAuthority, Dutch railway operators]
  • A. codeOn
    Indicates that one entity writes, develops, or modifies software using or for another entity (such as a platform, project, or codebase).
  • B. authorityCode chosen
    Indicates that an entity is identified or classified by a specific code assigned by an authoritative body or governing standard.
  • C. codingDomain
    Indicates that an entity operates within, pertains to, or is characterized by a particular domain or field of coding or programming.
  • D. code
    Indicates that an entity writes, develops, or produces computer software or source code.
  • E. codifiedUnderAuthority
    Indicates that something has been formally established, defined, or recorded according to the rules or power of a specific authority.
  • 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_69f76e76d10881909ec1679bc043108c completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f7c9f5a8848190ba956ff27f44e396 completed May 3, 2026, 10:19 p.m.
PD Predicate disambiguation batch_69f7c8999a348190abc1895eaa6e036d completed May 3, 2026, 10:13 p.m.
Created at: May 3, 2026, 4:12 p.m.