Triple

T22593788
Position Surface form Disambiguated ID Type / Status
Subject Ulaanbaatar Railway E574617 entity
Predicate hasAbbreviation P43 FINISHED
Object UBTZ (commonly used Latin transliteration)
UBTZ is the commonly used Latin-script abbreviation for the Ulaanbaatar Railway, the national railway operator of Mongolia.
 E1544772 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: UBTZ (commonly used Latin transliteration) | Statement: [Ulaanbaatar Railway, hasAbbreviation, UBTZ (commonly used Latin transliteration)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UBTZ (commonly used Latin transliteration)
Context triple: [Ulaanbaatar Railway, hasAbbreviation, UBTZ (commonly used Latin transliteration)]
  • A. Bashkir Latin alphabet
    The Bashkir Latin alphabet is a historical writing system that once represented the Bashkir language using Latin script before it was replaced by the modern Cyrillic-based alphabet.
  • B. uB
    uB is the commonly used abbreviation for the University of Burgundy, a public university located in Dijon, France.
  • C. Belarusian Latin alphabet
    The Belarusian Latin alphabet is an alternative writing system for the Belarusian language that uses Latin script instead of Cyrillic and has been employed in various historical, cultural, and diaspora contexts.
  • D. Uzbek Latin script
    The Uzbek Latin script is the modern Latin-based writing system officially used for the Uzbek language in Uzbekistan.
  • E. UZT
    UZT is the time zone used in Uzbekistan, corresponding to UTC+5 hours.
  • 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: UBTZ (commonly used Latin transliteration)
Triple: [Ulaanbaatar Railway, hasAbbreviation, UBTZ (commonly used Latin transliteration)]
Generated description
UBTZ is the commonly used Latin-script abbreviation for the Ulaanbaatar Railway, the national railway operator of Mongolia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UBTZ (commonly used Latin transliteration)
Target entity description: UBTZ is the commonly used Latin-script abbreviation for the Ulaanbaatar Railway, the national railway operator of Mongolia.
  • A. Bashkir Latin alphabet
    The Bashkir Latin alphabet is a historical writing system that once represented the Bashkir language using Latin script before it was replaced by the modern Cyrillic-based alphabet.
  • B. uB
    uB is the commonly used abbreviation for the University of Burgundy, a public university located in Dijon, France.
  • C. Belarusian Latin alphabet
    The Belarusian Latin alphabet is an alternative writing system for the Belarusian language that uses Latin script instead of Cyrillic and has been employed in various historical, cultural, and diaspora contexts.
  • D. Uzbek Latin script
    The Uzbek Latin script is the modern Latin-based writing system officially used for the Uzbek language in Uzbekistan.
  • E. UZT
    UZT is the time zone used in Uzbekistan, corresponding to UTC+5 hours.
  • 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_69e245bc11308190b69d794d5d1e0bb6 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f16163cb248190b377b110d80a6730 completed April 29, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b3d5e31308190a11bff9270795efd completed May 18, 2026, 4:25 p.m.
NEDg Description generation batch_6a0b3e908a308190af37f63904f38915 completed May 18, 2026, 4:30 p.m.
NED2 Entity disambiguation (via description) batch_6a0b3f8d85cc8190812924d466d18735 completed May 18, 2026, 4:34 p.m.
Created at: April 17, 2026, 2:49 p.m.