Triple

T13247678
Position Surface form Disambiguated ID Type / Status
Subject Fanny Blankers-Koen Games E315447 entity
Predicate location P40 FINISHED
Object Hengelo NE NERFINISHED

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: Hengelo | Statement: [Fanny Blankers-Koen Games, location, Hengelo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hengelo
Context triple: [Fanny Blankers-Koen Games, location, Hengelo]
  • A. Hengelo chosen
    Hengelo is a city and municipality in the Dutch province of Overijssel, known as an important industrial and regional center in the Twente area.
  • B. Woerden
    Woerden is a historic Dutch city and municipality in the central Netherlands, known for its medieval fortifications and traditional cheese market.
  • C. Heemskerk
    Heemskerk is a town and municipality in North Holland in the Netherlands, known for its coastal dunes, historic estates, and residential character.
  • D. Harderwijk
    Harderwijk is a historic Dutch city known for its former Hanseatic trading role and scenic location on the shores of the Veluwemeer.
  • E. Hoorn
    Hoorn is a historic port city in the Netherlands known for its role in the Dutch Golden Age and as a former base of the Dutch East India Company.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d806b1072881909e46bd212259c5f0 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98d5c09f88190bb1566a6d8c073a6 completed April 10, 2026, 11:53 p.m.
Created at: April 9, 2026, 9:23 p.m.