Triple

T701058
Position Surface form Disambiguated ID Type / Status
Subject DS Logon E13998 entity
Predicate loginScope P18411 FINISHED
Object multiple DoD and VA web applications 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: multiple DoD and VA web applications | Statement: [DS Logon, loginScope, multiple DoD and VA web applications]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: loginScope
Context triple: [DS Logon, loginScope, multiple DoD and VA web applications]
  • A. securityRole
    Indicates that an entity holds a specific security-related role, permission level, or access profile within a system or context.
  • B. locationScope
    Indicates the specific geographic or spatial area within which a given relationship, condition, or action is considered valid or applicable.
  • C. organizationalScope
    Indicates the range or extent of responsibility, authority, or applicability that an action, policy, or relationship has within an organization or its sub-units.
  • D. identityComponent
    Indicates that one entity functions as an identifying or defining part of another entity, contributing to its overall identity.
  • E. identityConcept
    Indicates that two concepts are the same in identity, representing exactly the same underlying idea or meaning.
  • 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_69a493494ec48190ae6751683625a9ba completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a544e3608190ac315c7aa9f88e7e completed March 1, 2026, 8:44 p.m.
PD Predicate disambiguation batch_69a4a4ec8c748190b198492a0eea4445 completed March 1, 2026, 8:43 p.m.
PDg Predicate description generation batch_69a4a54235548190b46218ea18f77341 completed March 1, 2026, 8:44 p.m.
Created at: March 1, 2026, 7:36 p.m.