Triple

T31113122
Position Surface form Disambiguated ID Type / Status
Subject Waldhof Mannheim E793008 entity
Predicate hasRivalriesRegion P80695 FINISHED
Object southwestern Germany 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: southwestern Germany | Statement: [Waldhof Mannheim, hasRivalriesRegion, southwestern Germany]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasRivalriesRegion
Context triple: [Waldhof Mannheim, hasRivalriesRegion, southwestern Germany]
  • A. rivalryRegion chosen
    Indicates a competitive or adversarial relationship that exists between entities within a specific geographic or regional context.
  • B. hasLocalRivalry
    Indicates that there is an ongoing competitive or adversarial relationship between entities that are geographically close or share the same local area.
  • C. hasInStateRivalries
    Indicates that two entities are rivals or competitors within the same state or internal jurisdiction.
  • D. hasRivalryCategory
    Indicates that there exists a competitive or adversarial relationship between entities that falls into a specific classified type or category of rivalry.
  • E. hasRivalryRoot
    Indicates that a rivalry relationship originates from, or is fundamentally based on, a particular source, cause, or underlying factor.
  • 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_69f224cfd5d881908ec6447bc321cd58 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f7764ab1fc81909f9348db87bd7692 completed May 3, 2026, 4:22 p.m.
PD Predicate disambiguation batch_69f76905d9c88190b1ee810bc9ab644f completed May 3, 2026, 3:25 p.m.
Created at: April 29, 2026, 9:04 p.m.