Triple

T789947
Position Surface form Disambiguated ID Type / Status
Subject Samegrelo E16889 entity
Predicate historicalName P65 FINISHED
Object Odishi
Odishi is the historical name for a region in western Georgia, corresponding largely to present-day Samegrelo and known for its distinct Mingrelian culture and history.
 E102468 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: Odishi | Statement: [Samegrelo, historicalName, Odishi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Odishi
Context triple: [Samegrelo, historicalName, Odishi]
  • A. Oshiwambo
    Oshiwambo is a Bantu language (or cluster of closely related dialects) widely spoken by the Ovambo people in northern Namibia and southern Angola.
  • B. Ndowe
    Ndowe is a Bantu language spoken by the Ndowe people along the coastal region of Equatorial Guinea.
  • C. Ngozi
    Ngozi is a Nigerian given name of Igbo origin commonly used for females and meaning "blessing."
  • D. Gwarinpa
    Gwarinpa is a large, planned residential district in Abuja, Nigeria, known for its extensive housing estates and relatively well-organized urban layout.
  • E. Beni
    Beni is a sparsely populated, largely Amazonian department in northeastern Bolivia known for its tropical lowlands, cattle ranching, and rich indigenous cultures.
  • 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: Odishi
Triple: [Samegrelo, historicalName, Odishi]
Generated description
Odishi is the historical name for a region in western Georgia, corresponding largely to present-day Samegrelo and known for its distinct Mingrelian culture and history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Odishi
Target entity description: Odishi is the historical name for a region in western Georgia, corresponding largely to present-day Samegrelo and known for its distinct Mingrelian culture and history.
  • A. Oshiwambo
    Oshiwambo is a Bantu language (or cluster of closely related dialects) widely spoken by the Ovambo people in northern Namibia and southern Angola.
  • B. Ndowe
    Ndowe is a Bantu language spoken by the Ndowe people along the coastal region of Equatorial Guinea.
  • C. Ngozi
    Ngozi is a Nigerian given name of Igbo origin commonly used for females and meaning "blessing."
  • D. Gwarinpa
    Gwarinpa is a large, planned residential district in Abuja, Nigeria, known for its extensive housing estates and relatively well-organized urban layout.
  • E. Beni
    Beni is a sparsely populated, largely Amazonian department in northeastern Bolivia known for its tropical lowlands, cattle ranching, and rich indigenous cultures.
  • 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_69a4936cb7448190914f5fe4b8d81607 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7841b0c8190859ecd247e32c6ec completed March 1, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7a3afbb0c8190b4e7aa7824c8b787 completed March 4, 2026, 3:14 a.m.
NEDg Description generation batch_69a7a6b6741081908d14a974a7f55fbc completed March 4, 2026, 3:27 a.m.
NED2 Entity disambiguation (via description) batch_69a7a8ad0c2c8190921ace3db1cd2608 completed March 4, 2026, 3:36 a.m.
Created at: March 1, 2026, 7:38 p.m.