Triple

T14225459
Position Surface form Disambiguated ID Type / Status
Subject Praga E352605 entity
Predicate hasPart P35 FINISHED
Object Saska Kępa
Saska Kępa is a leafy, upscale residential neighborhood in Warsaw known for its modernist villas, cosmopolitan atmosphere, and vibrant café and restaurant scene.
E1087238 NE FINISHED

How this triple was built (4 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: Saska Kępa | Statement: [Praga, hasPart, Saska Kępa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saska Kępa
Context triple: [Praga, hasPart, Saska Kępa]
  • A. Kornat
    Kornat is the largest and most prominent island in Croatia’s Kornati archipelago, known for its rugged coastline and inclusion within Kornati National Park.
  • B. Białołęka
    Białołęka is a rapidly developing residential district in the northeastern part of Warsaw, known for its modern housing estates and expanding infrastructure.
  • C. Skawica
    Skawica is a village in southern Poland, located in the Lesser Poland Voivodeship within the administrative district of powiat suski.
  • D. Ciechocinek
    Ciechocinek is a Polish spa town renowned for its historic saline graduation towers and therapeutic health resorts.
  • E. Kopaska
    Kopaska is the Indonesian Navy’s elite frogman and special operations unit, specializing in underwater demolition, maritime sabotage, and counter-terrorism missions.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Saska Kępa
Triple: [Praga, hasPart, Saska Kępa]
Generated description
Saska Kępa is a leafy, upscale residential neighborhood in Warsaw known for its modernist villas, cosmopolitan atmosphere, and vibrant café and restaurant scene.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saska Kępa
Target entity description: Saska Kępa is a leafy, upscale residential neighborhood in Warsaw known for its modernist villas, cosmopolitan atmosphere, and vibrant café and restaurant scene.
  • A. Kornat
    Kornat is the largest and most prominent island in Croatia’s Kornati archipelago, known for its rugged coastline and inclusion within Kornati National Park.
  • B. Białołęka
    Białołęka is a rapidly developing residential district in the northeastern part of Warsaw, known for its modern housing estates and expanding infrastructure.
  • C. Skawica
    Skawica is a village in southern Poland, located in the Lesser Poland Voivodeship within the administrative district of powiat suski.
  • D. Ciechocinek
    Ciechocinek is a Polish spa town renowned for its historic saline graduation towers and therapeutic health resorts.
  • E. Kopaska
    Kopaska is the Indonesian Navy’s elite frogman and special operations unit, specializing in underwater demolition, maritime sabotage, and counter-terrorism missions.
  • F. None of above. chosen

Provenance (5 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_69d8278a06e481908b5d6af0a8afe737 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6228e53c8190abbe4e2d88a7362a completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd281611b48190b787e38ba9c733a4 completed May 8, 2026, 12:02 a.m.
NEDg Description generation batch_69fd2a5c80308190868967a402c5fa42 completed May 8, 2026, 12:12 a.m.
NED2 Entity disambiguation (via description) batch_69fd2af4ddf8819089435b849415b941 completed May 8, 2026, 12:14 a.m.
Created at: April 10, 2026, 1:06 a.m.