Triple

T16199704
Position Surface form Disambiguated ID Type / Status
Subject Line B (Prague Metro) E393164 entity
Predicate servesStation P839 FINISHED
Object Anděl
Anděl is a major Prague Metro station and busy transport hub located in the Smíchov district of the city.
E1198644 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: Anděl | Statement: [Line B (Prague Metro), servesStation, Anděl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anděl
Context triple: [Line B (Prague Metro), servesStation, Anděl]
  • A. Arcángel
    Arcángel is a Puerto Rican-American reggaeton and Latin trap singer and songwriter known for his influential role in the urban Latin music scene.
  • B. Artangel
    Artangel is a London-based arts organization known for producing ambitious, site-specific and often socially engaged contemporary art projects.
  • C. El Ángel
    El Ángel is a famous victory column and iconic symbol of Mexico City commemorating the country’s independence.
  • D. Angeliké
    Angeliké is a variant spelling of the given name Angélique, a feminine name of French origin derived from the word for "angelic."
  • E. Archangel
    Archangel is a virtual reality mech combat game developed by Skydance Interactive, featuring story-driven missions and large-scale mechanized warfare.
  • 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: Anděl
Triple: [Line B (Prague Metro), servesStation, Anděl]
Generated description
Anděl is a major Prague Metro station and busy transport hub located in the Smíchov district of the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anděl
Target entity description: Anděl is a major Prague Metro station and busy transport hub located in the Smíchov district of the city.
  • A. Arcángel
    Arcángel is a Puerto Rican-American reggaeton and Latin trap singer and songwriter known for his influential role in the urban Latin music scene.
  • B. Artangel
    Artangel is a London-based arts organization known for producing ambitious, site-specific and often socially engaged contemporary art projects.
  • C. El Ángel
    El Ángel is a famous victory column and iconic symbol of Mexico City commemorating the country’s independence.
  • D. Angeliké
    Angeliké is a variant spelling of the given name Angélique, a feminine name of French origin derived from the word for "angelic."
  • E. Archangel
    Archangel is a virtual reality mech combat game developed by Skydance Interactive, featuring story-driven missions and large-scale mechanized warfare.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222de2db481908471b9c73d444607 completed April 17, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffff1107908190afda091b53317d81 completed May 10, 2026, 3:44 a.m.
NEDg Description generation batch_6a00014d982881908dcb9a0abd75a1e2 completed May 10, 2026, 3:53 a.m.
NED2 Entity disambiguation (via description) batch_6a00021e42ec8190af9869b7f8be3ce5 completed May 10, 2026, 3:57 a.m.
Created at: April 10, 2026, 5:03 a.m.