Triple

T37836662

Position	Surface form	Disambiguated ID	Type / Status
Subject	ლევან კობიაშვილი	`E943355`	entity
Predicate	საკლუბო_კარიერა_დაიწყო	`P78185`	FINISHED
Object	მერანი თბილისი მერანი თბილისი არის თბილისის საფეხბურთო კლუბი, სადაც კარიერა დაიწყო ლევან კობიაშვილმა.	`E2245267`	NE FINISHED

How this triple was built (3 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: მერანი თბილისი | Statement: [ლევან კობიაშვილი, საკლუბო_კარიერა_დაიწყო, მერანი თბილისი]

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: მერანი თბილისი
Triple: [ლევან კობიაშვილი, საკლუბო_კარიერა_დაიწყო, მერანი თბილისი]

Generated description

მერანი თბილისი არის თბილისის საფეხბურთო კლუბი, სადაც კარიერა დაიწყო ლევან კობიაშვილმა.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: საკლუბო_კარიერა_დაიწყო
Context triple: [ლევან კობიაშვილი, საკლუბო_კარიერა_დაიწყო, მერანი თბილისი]

A. clubCareerStart chosen
Indicates the point in time when an entity begins its professional or organized club-level career.
B. beganBroadcastingCareer
Indicates that an entity started or initiated its professional career in broadcasting at a particular time or context.
C. startedCupCareer
Indicates that an entity began its participation or professional involvement in a cup-based competition or series at a specified time or event.
D. launchedCareerOf
Indicates that one entity’s actions, support, or involvement initiated or significantly advanced another entity’s professional career.
E. associatedClubBeganPlay
Indicates that the related club began its competitive play or official participation at the specified time.
F. None of above.

Provenance (6 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_69f76eeb0f7081908d6d3adbc469889c`	completed	May 3, 2026, 3:51 p.m.
NER	Named-entity recognition	`batch_69fbbae559a8819086ef839973f8d9b2`	completed	May 6, 2026, 10:04 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a40fb889d04819089c1c1651fc7da9b`	completed	June 28, 2026, 10:46 a.m.
NEDg	Description generation	`batch_6a40fc7bafb881909b38b069fea8e54b`	completed	June 28, 2026, 10:50 a.m.
NED2	Entity disambiguation (via description)	`batch_6a40fce18ec08190946c064d27fcf5ad`	completed	June 28, 2026, 10:52 a.m.
PD	Predicate disambiguation	`batch_69fbb1440fa08190abf25ba684f75b6e`	completed	May 6, 2026, 9:23 p.m.

Created at: May 3, 2026, 4:19 p.m.