Triple

T8587642
Position Surface form Disambiguated ID Type / Status
Subject Presidentinlinna E203345 entity
Predicate location P40 FINISHED
Object Kauppatori E746166 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: Kauppatori | Statement: [Presidentinlinna, location, Kauppatori]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kauppatori
Context triple: [Presidentinlinna, location, Kauppatori]
  • A. Kauppatori chosen
    Kauppatori is Helsinki’s central seaside market square, known for its outdoor stalls, food vendors, and role as a major tourist and transport hub by the harbor.
  • B. Nagyvásárcsarnok
    Nagyvásárcsarnok is Budapest’s largest and most famous indoor market hall, renowned for its grand 19th-century architecture and bustling food and craft stalls.
  • C. Valbo Köpcentrum
    Valbo Köpcentrum is a major regional shopping mall in Valbo, Sweden, featuring a wide range of retail stores, services, and dining options.
  • D. Rossmarkt
    Rossmarkt is a central public square in Frankfurt am Main known for its historical significance and role as a busy commercial and transit hub.
  • E. The Mart
    The Mart is a massive commercial building in Chicago, historically known as the Merchandise Mart, that serves as a major hub for wholesale showrooms, offices, and design centers.
  • 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_69ca8329bb7c8190a63c643730839103 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc457dc76481908ec5ee31ad72e887 completed March 31, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebb9716948190b0eb61ddf25fb333 completed April 2, 2026, 6:55 p.m.
Created at: March 30, 2026, 6:23 p.m.