Triple

T8754686
Position Surface form Disambiguated ID Type / Status
Subject GAZ Group E208044 entity
Predicate brand P1500 FINISHED
Object LiAZ
LiAZ is a Russian bus manufacturer known for producing urban and intercity buses widely used across Russia and neighboring countries.
 E754546 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: LiAZ | Statement: [GAZ Group, brand, LiAZ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LiAZ
Context triple: [GAZ Group, brand, LiAZ]
  • A. LAZ
    LAZ is the station code for San Lázaro, a Mexico City Metro station serving Line 1 and Line B near the city’s eastern transport hubs.
  • B. Laz
    Laz is a South Caucasian (Kartvelian) language traditionally spoken by the Laz people along the southeastern Black Sea coast, particularly in northeastern Turkey and parts of Georgia.
  • C. Lazi
    Lazi is a coastal municipality on the southeastern side of Siquijor Island in the Philippines, known for its historic church, natural springs, and waterfalls.
  • D. Laris
    Laris is a Romulan former Tal Shiar operative who serves as Jean-Luc Picard’s loyal housekeeper, confidante, and ally in the series Star Trek: Picard.
  • E. LZ-40
    LZ-40 is a road on the island of Lanzarote in Spain’s Canary Islands, serving as one of the main access routes to the resort town of Puerto del Carmen.
  • 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: LiAZ
Triple: [GAZ Group, brand, LiAZ]
Generated description
LiAZ is a Russian bus manufacturer known for producing urban and intercity buses widely used across Russia and neighboring countries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LiAZ
Target entity description: LiAZ is a Russian bus manufacturer known for producing urban and intercity buses widely used across Russia and neighboring countries.
  • A. LAZ
    LAZ is the station code for San Lázaro, a Mexico City Metro station serving Line 1 and Line B near the city’s eastern transport hubs.
  • B. Laz
    Laz is a South Caucasian (Kartvelian) language traditionally spoken by the Laz people along the southeastern Black Sea coast, particularly in northeastern Turkey and parts of Georgia.
  • C. Lazi
    Lazi is a coastal municipality on the southeastern side of Siquijor Island in the Philippines, known for its historic church, natural springs, and waterfalls.
  • D. Laris
    Laris is a Romulan former Tal Shiar operative who serves as Jean-Luc Picard’s loyal housekeeper, confidante, and ally in the series Star Trek: Picard.
  • E. LZ-40
    LZ-40 is a road on the island of Lanzarote in Spain’s Canary Islands, serving as one of the main access routes to the resort town of Puerto del Carmen.
  • 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_69ca835cd6b08190bd7c63db92f53c86 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5dd83088819082cf54adc0c04243 completed March 31, 2026, 11:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf43305664819085e762e42b138754 completed April 3, 2026, 4:33 a.m.
NEDg Description generation batch_69cf452b237c8190958f7b42e9611e7b completed April 3, 2026, 4:42 a.m.
NED2 Entity disambiguation (via description) batch_69cf45e6f4108190ac6955264b466abb completed April 3, 2026, 4:45 a.m.
Created at: March 30, 2026, 6:39 p.m.