Triple

T11068155
Position Surface form Disambiguated ID Type / Status
Subject Southern Tat E261676 entity
Predicate glottologName P6521 FINISHED
Object Tat-Southern
Tat-Southern is a variety of the Tat language, an Iranian language spoken primarily by Tat communities in the South Caucasus region.
E903153 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: Tat-Southern | Statement: [Southern Tat, glottologName, Tat-Southern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tat-Southern
Context triple: [Southern Tat, glottologName, Tat-Southern]
  • A. Tanno
    Tanno is a district or locality within the city of Kitami in Hokkaido, Japan.
  • B. Tzia
    Tzia is an alternative name for Kea, a Greek island in the Cyclades known for its traditional villages, beaches, and proximity to Athens.
  • C. Tawu
    Tawu is the indigenous name used by the Tao people, an Austronesian ethnic group native to Orchid Island in Taiwan.
  • D. Sosoxui
    Sosoxui is the endonym (native name) used by the Susu people for their own language and identity.
  • E. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • 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: Tat-Southern
Triple: [Southern Tat, glottologName, Tat-Southern]
Generated description
Tat-Southern is a variety of the Tat language, an Iranian language spoken primarily by Tat communities in the South Caucasus region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tat-Southern
Target entity description: Tat-Southern is a variety of the Tat language, an Iranian language spoken primarily by Tat communities in the South Caucasus region.
  • A. Tanno
    Tanno is a district or locality within the city of Kitami in Hokkaido, Japan.
  • B. Tzia
    Tzia is an alternative name for Kea, a Greek island in the Cyclades known for its traditional villages, beaches, and proximity to Athens.
  • C. Tawu
    Tawu is the indigenous name used by the Tao people, an Austronesian ethnic group native to Orchid Island in Taiwan.
  • D. Sosoxui
    Sosoxui is the endonym (native name) used by the Susu people for their own language and identity.
  • E. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • 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_69d6aa9983c08190b0ef61603b69feac completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7992164d88190a01ed567b2529227 completed April 9, 2026, 12:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c8b2d6e881909eeddf1e6427ad5c completed April 18, 2026, 6:08 p.m.
NEDg Description generation batch_69e3cae07b648190b4c0d2514712d6bd completed April 18, 2026, 6:18 p.m.
NED2 Entity disambiguation (via description) batch_69e3cf1f508c81909b4ca8131b7fc9ee completed April 18, 2026, 6:36 p.m.
Created at: April 8, 2026, 9:26 p.m.