Triple

T16089478
Position Surface form Disambiguated ID Type / Status
Subject Line A (Prague Metro) E390322 entity
Predicate hasStation P35 FINISHED
Object Flora
Flora is a Prague Metro station on Line A serving the Vinohrady district and connected to the Atrium Flora shopping center.
E1192853 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: Flora | Statement: [Line A (Prague Metro), hasStation, Flora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flora
Context triple: [Line A (Prague Metro), hasStation, Flora]
  • A. Flora
    Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
  • B. Flora
    Flora is the young niece in Henry James's novella "The Turn of the Screw," whose eerie innocence and ambiguous relationship to the supernatural are central to the story's psychological horror.
  • C. Flora
    Flora is the middle name of Ruth Disney, the daughter of Walt Disney and his wife Lillian.
  • D. Flora
    Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
  • E. Flora
    Flora is one of the three good fairies who serve as royal advisors and magical guardians in the animated children's series "Sofia the First."
  • 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: Flora
Triple: [Line A (Prague Metro), hasStation, Flora]
Generated description
Flora is a Prague Metro station on Line A serving the Vinohrady district and connected to the Atrium Flora shopping center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Flora
Target entity description: Flora is a Prague Metro station on Line A serving the Vinohrady district and connected to the Atrium Flora shopping center.
  • A. Flora
    Flora is a rural municipality in the province of Apayao in the Cordillera Administrative Region of the Philippines.
  • B. Flora
    Flora is a feminine given name of Latin origin meaning "flower," historically associated with the Roman goddess of flowers and spring.
  • C. Flora
    Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
  • D. Flora
    Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
  • E. Flora
    Flora is one of the three good fairies in Disney's "Sleeping Beauty," known for her red attire, leadership among the fairies, and role in protecting Princess Aurora.
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1845161908190adca2af94710b2cc completed April 17, 2026, 12:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe490d494819081f812811f032702 completed May 10, 2026, 1:51 a.m.
NEDg Description generation batch_69ffe63f757c81908c7dc3c5ae3075c6 completed May 10, 2026, 1:58 a.m.
NED2 Entity disambiguation (via description) batch_69ffe6b3f25481908dd4b6108b5d95c0 completed May 10, 2026, 2 a.m.
Created at: April 10, 2026, 4:59 a.m.