Triple

T4933580
Position Surface form Disambiguated ID Type / Status
Subject Kyiv Oblast E110754 entity
Predicate contains P35 FINISHED
Object Fastiv
Fastiv is a historic city in northern Ukraine known as a regional railway hub and industrial center southwest of Kyiv.
 E481917 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: Fastiv | Statement: [Kyiv Oblast, contains, Fastiv]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fastiv
Context triple: [Kyiv Oblast, contains, Fastiv]
  • A. Speedy
    Speedy is a 1928 silent comedy film starring Harold Lloyd, known for its energetic New York City setting and memorable Coney Island and baseball sequences.
  • B. Quick
    Quick is the fast-talking, street-smart protagonist played by Eddie Murphy in the 1989 crime-comedy film "Harlem Nights."
  • C. Vitesse
    Vitesse is a professional Dutch football club based in Arnhem that competes in the country's top leagues and European competitions.
  • D. Fast Life
    "Fast Life" is a hip-hop track by American rapper Paul Wall that showcases his signature Southern rap style and themes of hustle and street luxury.
  • E. SPEED
    SPEED was an American cable and satellite television network focused on motorsports and automotive programming.
  • 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: Fastiv
Triple: [Kyiv Oblast, contains, Fastiv]
Generated description
Fastiv is a historic city in northern Ukraine known as a regional railway hub and industrial center southwest of Kyiv.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fastiv
Target entity description: Fastiv is a historic city in northern Ukraine known as a regional railway hub and industrial center southwest of Kyiv.
  • A. Speedy
    Speedy is a 1928 silent comedy film starring Harold Lloyd, known for its energetic New York City setting and memorable Coney Island and baseball sequences.
  • B. Quick
    Quick is the fast-talking, street-smart protagonist played by Eddie Murphy in the 1989 crime-comedy film "Harlem Nights."
  • C. Vitesse
    Vitesse is a professional Dutch football club based in Arnhem that competes in the country's top leagues and European competitions.
  • D. Fast Life
    "Fast Life" is a hip-hop track by American rapper Paul Wall that showcases his signature Southern rap style and themes of hustle and street luxury.
  • E. SPEED
    SPEED was an American cable and satellite television network focused on motorsports and automotive programming.
  • 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_69bd4415190c8190817bee7ec9f9f944 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd70652d988190ba4a493db510952e completed March 20, 2026, 4:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77b41c4c8190b4f714334242bc9b completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be7b9611a881908e83086719406145 completed March 21, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_69be7ce630248190b274547eaa15fe85 completed March 21, 2026, 11:11 a.m.
Created at: March 20, 2026, 1:30 p.m.