Triple

T8956306
Position Surface form Disambiguated ID Type / Status
Subject ICERD E213478 entity
Predicate individualCommunicationsProcedureArticle P85860 FINISHED
Object Article 14 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: Article 14 | Statement: [ICERD, individualCommunicationsProcedureArticle, Article 14]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: individualCommunicationsProcedureArticle
Context triple: [ICERD, individualCommunicationsProcedureArticle, Article 14]
  • A. article9Provision
    Indicates a relationship where a specific legal or contractual element is identified as a provision contained within Article 9 of a larger document or agreement.
  • B. implementsArticle
    Indicates that one entity carries out, realizes, or puts into practice the content, requirements, or provisions specified by a particular article.
  • C. articleOrParagraph
    Indicates that one entity is either an entire article or a specific paragraph within an article in relation to another entity.
  • D. relationshipToArticle41
    Indicates the specific legal or contextual connection an entity has to Article 41 (such as being governed by, subject to, or derived from that article).
  • E. articleContent
    Indicates that one entity is the textual or media content that makes up the body of another entity, typically an article or document.
  • 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_69ca8399ad2081909f8fa41d4314c215 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6728965881908e9f14aaee0c5a18 completed April 1, 2026, 12:30 a.m.
PD Predicate disambiguation batch_69cc5ed74d288190b712d739805579dc completed March 31, 2026, 11:55 p.m.
PDg Predicate description generation batch_69cc5f887108819096d45a186fc137b3 completed March 31, 2026, 11:58 p.m.
Created at: March 30, 2026, 7 p.m.