Triple

T22438574
Position Surface form Disambiguated ID Type / Status
Subject Division of Training and Development E554692 entity
Predicate abbreviation P43 FINISHED
Object DTD 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: DTD | Statement: [Division of Training and Development, abbreviation, DTD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DTD
Context triple: [Division of Training and Development, abbreviation, DTD]
  • A. DTD
    DTD (Document Type Definition) is an XML schema language used to define the legal structure, elements, and attributes of an XML document.
  • B. DTD chosen
    DTD is the abbreviated name for the Division of Training and Development, an organizational unit focused on designing and delivering training and professional development programs.
  • C. DTML
    DTML (Document Template Markup Language) is a server-side scripting and templating language used in the Zope web application framework to generate dynamic web content.
  • D. SGML
    SGML (Standard Generalized Markup Language) is a standardized metalanguage for defining markup languages used to structure and describe the content of electronic documents.
  • E. DITA
    DITA (Darwin Information Typing Architecture) is an XML-based standard for authoring, structuring, and publishing modular technical documentation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ae01bd08190aee5141f4c0848bc completed April 29, 2026, 1:12 a.m.
Created at: April 16, 2026, 8:47 p.m.