Triple

T15795327
Position Surface form Disambiguated ID Type / Status
Subject მთაწმინდა E382961 entity
Predicate near P350 FINISHED
Object სოლოლაკი
სოლოლაკი არის თბილისის ისტორიული უბანი, რომელიც გამოირჩევა ძველი არქიტექტურითა და ქალაქის ცენტრთან სიახლოვით.
 E1176682 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: სოლოლაკი | Statement: [მთაწმინდა, near, სოლოლაკი]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: სოლოლაკი
Context triple: [მთაწმინდა, near, სოლოლაკი]
  • A. Saarloq
    Saarloq is a small coastal settlement in southern Greenland known for its remote location and traditional Greenlandic lifestyle.
  • B. Lalsalu
    Lalsalu is a classic Bengali novel by Syed Waliullah that explores religious hypocrisy and rural life in East Bengal.
  • C. Sa’luk
    Sa’luk is a ruthless and treacherous member of the Forty Thieves who serves as the main villain in Disney’s animated film "Aladdin and the King of Thieves."
  • D. Lolak
    Lolak is a town in North Sulawesi, Indonesia, serving as the administrative and political center of Bolaang Mongondow Regency.
  • E. Laiolo
    Laiolo is an alternate name for the Laiyolo language, an Austronesian language spoken in parts of Indonesia.
  • 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: სოლოლაკი
Triple: [მთაწმინდა, near, სოლოლაკი]
Generated description
სოლოლაკი არის თბილისის ისტორიული უბანი, რომელიც გამოირჩევა ძველი არქიტექტურითა და ქალაქის ცენტრთან სიახლოვით.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: სოლოლაკი
Target entity description: სოლოლაკი არის თბილისის ისტორიული უბანი, რომელიც გამოირჩევა ძველი არქიტექტურითა და ქალაქის ცენტრთან სიახლოვით.
  • A. Saarloq
    Saarloq is a small coastal settlement in southern Greenland known for its remote location and traditional Greenlandic lifestyle.
  • B. Lalsalu
    Lalsalu is a classic Bengali novel by Syed Waliullah that explores religious hypocrisy and rural life in East Bengal.
  • C. Sa’luk
    Sa’luk is a ruthless and treacherous member of the Forty Thieves who serves as the main villain in Disney’s animated film "Aladdin and the King of Thieves."
  • D. Lolak
    Lolak is a town in North Sulawesi, Indonesia, serving as the administrative and political center of Bolaang Mongondow Regency.
  • E. Laiolo
    Laiolo is an alternate name for the Laiyolo language, an Austronesian language spoken in parts of Indonesia.
  • 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_69d86da16e188190b89af699f1ed0bfe completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0b4dc887081909d682ae153f06d97 completed April 16, 2026, 10:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff90aea81c8190ad8bc0cdedf4b77a completed May 9, 2026, 7:53 p.m.
NEDg Description generation batch_69ff93b24828819092841bc02059995d completed May 9, 2026, 8:06 p.m.
NED2 Entity disambiguation (via description) batch_69ff9435b800819093985b293a541e46 completed May 9, 2026, 8:08 p.m.
Created at: April 10, 2026, 4:48 a.m.