Triple

T20597024
Position Surface form Disambiguated ID Type / Status
Subject Ushba E506074 entity
Predicate visibleFrom P1165 FINISHED
Object Mazeri
Mazeri is a village in Georgia’s Svaneti region, known as a base for trekking and for its scenic views of the Ushba mountain massif.
 E1439276 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: Mazeri | Statement: [Ushba, visibleFrom, Mazeri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mazeri
Context triple: [Ushba, visibleFrom, Mazeri]
  • A. Mazzoli
    Mazzoli is an Italian surname associated with various notable individuals, including politicians and artists.
  • B. Molinaro
    Molinaro is an Italian occupational surname, historically associated with millers and derived from the same root as "Molinero."
  • C. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • D. Mazin
    Mazin is a surname most prominently associated with Craig Mazin, an American screenwriter and producer known for works like the HBO miniseries "Chernobyl" and the series "The Last of Us."
  • E. Zaqueri
    Zaqueri "Aphromoo" Black is a prominent American professional League of Legends player best known for his long-standing career as a support and his charismatic presence in the esports scene.
  • 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: Mazeri
Triple: [Ushba, visibleFrom, Mazeri]
Generated description
Mazeri is a village in Georgia’s Svaneti region, known as a base for trekking and for its scenic views of the Ushba mountain massif.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mazeri
Target entity description: Mazeri is a village in Georgia’s Svaneti region, known as a base for trekking and for its scenic views of the Ushba mountain massif.
  • A. Mazzoli
    Mazzoli is an Italian surname associated with various notable individuals, including politicians and artists.
  • B. Molinaro
    Molinaro is an Italian occupational surname, historically associated with millers and derived from the same root as "Molinero."
  • C. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • D. Mazin
    Mazin is a surname most prominently associated with Craig Mazin, an American screenwriter and producer known for works like the HBO miniseries "Chernobyl" and the series "The Last of Us."
  • E. Zaqueri
    Zaqueri "Aphromoo" Black is a prominent American professional League of Legends player best known for his long-standing career as a support and his charismatic presence in the esports scene.
  • 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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa1d15b08190a720fc7cefbf333e completed April 20, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08b3ef3a8881908dea28ebbe7a8398 completed May 16, 2026, 6:14 p.m.
NEDg Description generation batch_6a08b475b1148190919ece9b4bcec385 completed May 16, 2026, 6:16 p.m.
NED2 Entity disambiguation (via description) batch_6a08b4f01f4c819088ae7637dcd9c6b7 completed May 16, 2026, 6:18 p.m.
Created at: April 16, 2026, 11:40 a.m.