Triple

T8200710
Position Surface form Disambiguated ID Type / Status
Subject Linn E191563 entity
Predicate hasGreenSpace P1495 FINISHED
Object Burgpark Linn E718610 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: Burgpark Linn | Statement: [Linn, hasGreenSpace, Burgpark Linn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burgpark Linn
Context triple: [Linn, hasGreenSpace, Burgpark Linn]
  • A. Burgpark Linn chosen
    Burgpark Linn is a historic park surrounding the medieval castle in the Krefeld district of Linn, Germany, known for its scenic grounds and cultural events.
  • B. The Glen
    The Glen is a residential neighborhood located adjacent to the Palacefields area.
  • C. The Glen
    The Glen is a historic public park in Dunfermline, Scotland, known for its landscaped grounds, woodland walks, and cultural significance as part of Pittencrieff Park.
  • D. Ewen Park
    Ewen Park is a public park in the Riverdale neighborhood of the Bronx known for its hilly terrain, open green spaces, and views over the Hudson River.
  • E. Bilston Glen
    Bilston Glen is a wooded valley in Midlothian, Scotland, known for its ancient woodland, wildlife, and history of environmental protest.
  • 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_69ca82c6e9548190a4c5ca14516e4417 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb5df6e7548190846a1afd62ec6d0a completed March 31, 2026, 5:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd34a9c8f08190a8a79b7baa7ffded completed April 1, 2026, 3:07 p.m.
Created at: March 30, 2026, 5:43 p.m.