Triple

T36479130
Position Surface form Disambiguated ID Type / Status
Subject Connecticut River navigation system E898759 entity
Predicate involvesEngineering P179173 FINISHED
Object channel improvement 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: channel improvement | Statement: [Connecticut River navigation system, involvesEngineering, channel improvement]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: involvesEngineering
Context triple: [Connecticut River navigation system, involvesEngineering, channel improvement]
  • A. engineeringWork chosen
    Indicates a relationship where an entity performs, produces, or is involved in an engineering-related task, project, or output.
  • B. engineeringEmphasis
    Indicates that something places a primary focus or specialization on engineering principles, methods, or activities.
  • C. engineeringBasis
    Indicates that something serves as the foundational technical or engineering rationale, justification, or underlying basis for another entity or decision.
  • D. engineeringContribution
    Indicates a relationship where an entity contributes engineering work, expertise, or effort toward the design, development, or improvement of another entity.
  • E. engineeringUse
    Indicates that one entity is used, applied, or employed in an engineering context by or for another entity.
  • 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_69f76e5a0e088190a2b6706aeb41723c completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69fe6c811bcc81908b1e1b1f8bcb071b completed May 8, 2026, 11:06 p.m.
PD Predicate disambiguation batch_69fe6c026d5481908b7a814dcf38c183 completed May 8, 2026, 11:04 p.m.
Created at: May 3, 2026, 4:10 p.m.