Triple

T33706381
Position Surface form Disambiguated ID Type / Status
Subject Ulsan E863602 entity
Predicate isGlobalHubFor P17291 FINISHED
Object automobile manufacturing 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: automobile manufacturing | Statement: [Ulsan, isGlobalHubFor, automobile manufacturing]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isGlobalHubFor
Context triple: [Ulsan, isGlobalHubFor, automobile manufacturing]
  • A. isProductionHubFor
    Indicates that a location or facility serves as a central site where goods, services, or content are primarily produced for another entity or region.
  • B. isCommunityHub
    Indicates that a place or entity functions as a central gathering point or focal location for community activities, services, and interactions.
  • C. isCommercialHubIn
    Indicates that a place functions as a primary center of commercial or business activity within a specified larger area or region.
  • D. Global HubLocation chosen
    Indicates a location that serves as a central, primary hub for global operations, connections, or activities.
  • E. isMajorHubInCountry
    Indicates that a location functions as a primary or central hub within a specified country, typically in terms of transport, commerce, or connectivity.
  • 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_69f3498844608190bb8f9b14908d2510 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6fab4f248819084f17495ac86e41a completed May 3, 2026, 7:35 a.m.
PD Predicate disambiguation batch_69f6f96dd4c8819093d6a7bd046a9ad5 completed May 3, 2026, 7:29 a.m.
Created at: May 1, 2026, 1:43 a.m.