Triple

T3940618
Position Surface form Disambiguated ID Type / Status
Subject Chrystie Street Connection E92023 entity
Predicate affectsServicePattern P20600 FINISHED
Object Manhattan Bridge subway services 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: Manhattan Bridge subway services | Statement: [Chrystie Street Connection, affectsServicePattern, Manhattan Bridge subway services]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: affectsServicePattern
Context triple: [Chrystie Street Connection, affectsServicePattern, Manhattan Bridge subway services]
  • A. includesServicePattern
    Indicates that one entity contains or incorporates a particular service pattern as part of its structure or configuration.
  • B. servesServicePattern
    Indicates that one entity provides or operates according to a particular service pattern or schedule for another.
  • C. hasServicePatternRole
    Indicates that an entity participates in a service pattern with a specific functional role or responsibility within that pattern.
  • D. hasServicePatternNote
    Indicates that a service pattern (such as a schedule or routing pattern) is associated with a specific explanatory note or annotation.
  • E. hasServicePatternChange chosen
    Indicates that there is a modification in the usual or scheduled pattern of a service’s operation.
  • 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_69aed965502c8190904ebad1203a4ae8 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeedfc88e4819084adefb695b975c5 completed March 9, 2026, 3:57 p.m.
PD Predicate disambiguation batch_69aee7625ad4819097e4e8a168c19274 completed March 9, 2026, 3:29 p.m.
Created at: March 9, 2026, 3:24 p.m.