Triple

T1854908
Position Surface form Disambiguated ID Type / Status
Subject Mkhedruli E41679 entity
Predicate usedForWriting P8571 FINISHED
Object Laz language
The Laz language is a South Caucasian (Kartvelian) minority language spoken mainly along the Black Sea coast of Turkey and Georgia.
 E207514 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: Laz language | Statement: [Mkhedruli, usedForWriting, Laz language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Laz language
Context triple: [Mkhedruli, usedForWriting, Laz language]
  • A. Lasalimu language
    The Lasalimu language is an Austronesian language spoken by a small community on Buton Island in Southeast Sulawesi, Indonesia.
  • B. Lakalai language
    The Lakalai language is an Austronesian language spoken by the Lakalai people of New Britain in Papua New Guinea.
  • C. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • D. Zabana language
    The Zabana language is an Oceanic language spoken primarily on Santa Isabel Island in the Solomon Islands.
  • E. Kumzari language
    The Kumzari language is an endangered Southwestern Iranian language spoken primarily by the Kumzari people in the Musandam Peninsula of Oman.
  • 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: Laz language
Triple: [Mkhedruli, usedForWriting, Laz language]
Generated description
The Laz language is a South Caucasian (Kartvelian) minority language spoken mainly along the Black Sea coast of Turkey and Georgia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Laz language
Target entity description: The Laz language is a South Caucasian (Kartvelian) minority language spoken mainly along the Black Sea coast of Turkey and Georgia.
  • A. Lasalimu language
    The Lasalimu language is an Austronesian language spoken by a small community on Buton Island in Southeast Sulawesi, Indonesia.
  • B. Lakalai language
    The Lakalai language is an Austronesian language spoken by the Lakalai people of New Britain in Papua New Guinea.
  • C. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • D. Zabana language
    The Zabana language is an Oceanic language spoken primarily on Santa Isabel Island in the Solomon Islands.
  • E. Kumzari language
    The Kumzari language is an endangered Southwestern Iranian language spoken primarily by the Kumzari people in the Musandam Peninsula of Oman.
  • 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_69a8864a83848190a4ec02721306c511 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb7c2354081909ee4da7669932796 completed March 7, 2026, 5:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1c89bdc8190acf517a7731fa5c7 completed March 8, 2026, 7:45 p.m.
NEDg Description generation batch_69add25c9c208190a576cf1123c0a2e6 completed March 8, 2026, 7:47 p.m.
NED2 Entity disambiguation (via description) batch_69add32803a48190b8ff08c605790f22 completed March 8, 2026, 7:51 p.m.
Created at: March 4, 2026, 7:33 p.m.