Triple

T3817694
Position Surface form Disambiguated ID Type / Status
Subject Prague Metro E84295 entity
Predicate hasStation P35 FINISHED
Object Dejvická
Dejvická is a metro station in Prague that serves as a key transport hub in the Dejvice district.
 E390329 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: Dejvická | Statement: [Prague Metro, hasStation, Dejvická]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dejvická
Context triple: [Prague Metro, hasStation, Dejvická]
  • A. Kriváň
    Kriváň is a prominent and symbolically important peak in Slovakia’s High Tatras, often regarded as a national symbol and popular hiking destination.
  • B. Vávrová
    Vávrová is a Czech surname most notably borne by Dana Vávrová, a well-known Czech-German actress and film director.
  • C. Zavacká
    Zavacká is the original Slovak family name of Julia Warhola, the mother of American pop artist Andy Warhol.
  • D. Lučina
    Lučina is a river in the Moravian-Silesian Region of the Czech Republic that flows through the city of Ostrava.
  • E. Jilava
    Jilava is a locality in Romania best known for its historic prison and fortress, which were used for political detentions and executions, especially during the 20th century.
  • 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: Dejvická
Triple: [Prague Metro, hasStation, Dejvická]
Generated description
Dejvická is a metro station in Prague that serves as a key transport hub in the Dejvice district.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dejvická
Target entity description: Dejvická is a metro station in Prague that serves as a key transport hub in the Dejvice district.
  • A. Kriváň
    Kriváň is a prominent and symbolically important peak in Slovakia’s High Tatras, often regarded as a national symbol and popular hiking destination.
  • B. Vávrová
    Vávrová is a Czech surname most notably borne by Dana Vávrová, a well-known Czech-German actress and film director.
  • C. Zavacká
    Zavacká is the original Slovak family name of Julia Warhola, the mother of American pop artist Andy Warhol.
  • D. Lučina
    Lučina is a river in the Moravian-Silesian Region of the Czech Republic that flows through the city of Ostrava.
  • E. Jilava
    Jilava is a locality in Romania best known for its historic prison and fortress, which were used for political detentions and executions, especially during the 20th century.
  • 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_69aed931f5908190be2c07af66d4df25 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeea5e41ec81908ed7e1ccc2713622 completed March 9, 2026, 3:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb43e1d481909a5b52cae5686179 completed March 14, 2026, 6:08 a.m.
NEDg Description generation batch_69b4fcec1cf48190aa0b128acb56c089 completed March 14, 2026, 6:15 a.m.
NED2 Entity disambiguation (via description) batch_69b4fd4d55248190bf4ef442a9991edf completed March 14, 2026, 6:16 a.m.
Created at: March 9, 2026, 3:17 p.m.