Triple

T50407
Position Surface form Disambiguated ID Type / Status
Subject Amsterdam E989 entity
Predicate hasSisterCity P919 FINISHED
Object Milan E11464 NE 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: Milan | Statement: [Amsterdam, hasSisterCity, Milan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milan
Context triple: [Amsterdam, hasSisterCity, Milan]
  • A. Milan chosen
    Milan is a major Italian metropolis renowned as a global center for fashion, design, finance, and culture.
  • B. Turin
    Turin is a major city in northern Italy known for its rich history, Baroque architecture, automotive industry, and role as a cultural and economic hub.
  • C. Naples
    Naples is a historic coastal city in southern Italy renowned for its rich cultural heritage, vibrant street life, and as the birthplace of pizza.
  • D. Venice
    Venice is a vibrant beachfront neighborhood on Los Angeles’s Westside known for its bohemian spirit, canals, boardwalk, and skate and surf culture.
  • E. Roma
    The Roma are a traditionally nomadic ethnic group originating from the Indian subcontinent and living mainly in Europe, long subjected to persecution and discrimination, including mass murder during the Holocaust.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a2480baefc81909951b14058479aa2 completed Feb. 28, 2026, 1:42 a.m.
NER Named-entity recognition batch_69a24ec333fc8190b66776b947e0bdbd completed Feb. 28, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2b85b11c08190b97de9b0382be6d5 completed Feb. 28, 2026, 9:41 a.m.
Created at: Feb. 28, 2026, 1:47 a.m.