Triple

T16747376
Position Surface form Disambiguated ID Type / Status
Subject DOI E406990 entity
Predicate resolvesVia P66401 FINISHED
Object Handle System E68554 NE FINISHED

How this triple was built (3 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: Handle System | Statement: [DOI, resolvesVia, Handle System]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Handle System
Context triple: [DOI, resolvesVia, Handle System]
  • A. Handle System chosen
    The Handle System is a global, distributed identifier system designed to provide persistent, secure, and scalable resolution of digital object identifiers on the internet.
  • B. System
    System is a core .NET namespace that provides fundamental classes and base types essential for building .NET applications.
  • C. System1
    System1 is a digital marketing and customer acquisition company specializing in data-driven advertising and online performance-based media.
  • D. Sistema
    Sistema is a consumer food storage and kitchenware brand known for its reusable plastic containers and lunch solutions.
  • E. Handle
    Handle is a dynamic, wheeled-legged robot developed by Boston Dynamics for agile material handling and warehouse automation tasks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: resolvesVia
Context triple: [DOI, resolvesVia, Handle System]
  • A. resolves
    Indicates that one entity successfully finds a solution, answer, or outcome for a problem, conflict, or uncertainty involving another entity.
  • B. resolvesTo chosen
    Indicates that one entity is mapped, translated, or evaluated into another specific entity as its target or result.
  • C. resolvesOver
    Indicates that one entity successfully addresses, settles, or overcomes an issue, conflict, or obstacle involving another entity or context.
  • D. resolvedIn
    Indicates that an issue, conflict, or process is brought to a conclusion or solution within a specified context, medium, or timeframe.
  • E. resolutionOf
    Indicates that one entity is the formal decision, outcome, or solution produced in response to, or for the purpose of addressing, another entity such as an issue, proposal, or problem.
  • F. None of above.

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_69d8838ffb088190a0b11149929006bf completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3aa2439848190a86a5bfc0702e2fe completed April 18, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a52033748190ae207d72d437236b completed May 10, 2026, 3:32 p.m.
PD Predicate disambiguation batch_69e319c807788190901250ab6e0ca55f completed April 18, 2026, 5:42 a.m.
Created at: April 10, 2026, 5:21 a.m.