Triple

T8797642
Position Surface form Disambiguated ID Type / Status
Subject Taunusstein E209327 entity
Predicate hasSubdivision P747 FINISHED
Object Orlen
Orlen is a district of the town of Taunusstein in the Rheingau-Taunus-Kreis region of Hesse, Germany.
E759643 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: Orlen | Statement: [Taunusstein, hasSubdivision, Orlen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orlen
Context triple: [Taunusstein, hasSubdivision, Orlen]
  • A. Łódź Fabryczna
    Łódź Fabryczna is a major modern railway terminus in Łódź, Poland, serving as one of the city’s primary long-distance and regional train hubs.
  • B. Kujawiak
    Kujawiak is a traditional Polish folk dance from the Kuyavia region, characterized by its slow, lyrical tempo and smooth, gliding movements.
  • C. Energetica
    Energetica is an interactive exhibition at Amsterdam’s NEMO Science Museum that explores the principles and applications of sustainable energy and natural forces.
  • D. UPC Polska
    UPC Polska is a leading Polish telecommunications company that provides broadband internet, digital television, and telephone services to households and businesses across Poland.
  • E. KGHM Polska Miedź
    KGHM Polska Miedź is a major Polish state-controlled mining and metallurgy company, and one of the world’s leading producers of copper and silver.
  • 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: Orlen
Triple: [Taunusstein, hasSubdivision, Orlen]
Generated description
Orlen is a district of the town of Taunusstein in the Rheingau-Taunus-Kreis region of Hesse, Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Orlen
Target entity description: Orlen is a district of the town of Taunusstein in the Rheingau-Taunus-Kreis region of Hesse, Germany.
  • A. Łódź Fabryczna
    Łódź Fabryczna is a major modern railway terminus in Łódź, Poland, serving as one of the city’s primary long-distance and regional train hubs.
  • B. Kujawiak
    Kujawiak is a traditional Polish folk dance from the Kuyavia region, characterized by its slow, lyrical tempo and smooth, gliding movements.
  • C. Energetica
    Energetica is an interactive exhibition at Amsterdam’s NEMO Science Museum that explores the principles and applications of sustainable energy and natural forces.
  • D. UPC Polska
    UPC Polska is a leading Polish telecommunications company that provides broadband internet, digital television, and telephone services to households and businesses across Poland.
  • E. KGHM Polska Miedź
    KGHM Polska Miedź is a major Polish state-controlled mining and metallurgy company, and one of the world’s leading producers of copper and silver.
  • 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_69ca836240888190a62b262e56a69d2f completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fa370d08190885ef65e3a3e56d3 completed March 31, 2026, 11:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf6f5d655881909013ac3e2ac0cebb completed April 3, 2026, 7:42 a.m.
NEDg Description generation batch_69cf71c118848190a937ecf714556ef3 completed April 3, 2026, 7:52 a.m.
NED2 Entity disambiguation (via description) batch_69cf744b17e88190b14607e6dff823a3 completed April 3, 2026, 8:03 a.m.
Created at: March 30, 2026, 6:44 p.m.