Triple
T5152442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senaki |
E116227
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object |
Mikha-Tskhali
Mikha-Tskhali is the historical name of the Georgian town now known as Senaki, located in the Samegrelo-Zemo Svaneti region of western Georgia.
|
E498547
|
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: Mikha-Tskhali | Statement: [Senaki, formerName, Mikha-Tskhali]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mikha-Tskhali Context triple: [Senaki, formerName, Mikha-Tskhali]
-
A.
Arsukidze
Arsukidze was a medieval Georgian architect renowned as the master builder of the Svetitskhoveli Cathedral in Mtskheta.
-
B.
Khatia
Khatia is a small gateway village that serves as one of the main entry points to Kanha National Park in central India.
-
C.
Merab
Merab is a figure in the Hebrew Bible known as one of King Saul’s daughters in the early monarchy of ancient Israel.
-
D.
Merkheuli
Merkheuli is a village in Abkhazia, Georgia, historically notable as the birthplace of Soviet security chief Lavrentiy Beria.
-
E.
Khvanchkara
Khvanchkara is a renowned semi-sweet red wine from Georgia, celebrated for its rich, fruity character and traditional production in the Racha region.
- 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: Mikha-Tskhali Triple: [Senaki, formerName, Mikha-Tskhali]
Generated description
Mikha-Tskhali is the historical name of the Georgian town now known as Senaki, located in the Samegrelo-Zemo Svaneti region of western Georgia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mikha-Tskhali Target entity description: Mikha-Tskhali is the historical name of the Georgian town now known as Senaki, located in the Samegrelo-Zemo Svaneti region of western Georgia.
-
A.
Arsukidze
Arsukidze was a medieval Georgian architect renowned as the master builder of the Svetitskhoveli Cathedral in Mtskheta.
-
B.
Khatia
Khatia is a small gateway village that serves as one of the main entry points to Kanha National Park in central India.
-
C.
Merab
Merab is a figure in the Hebrew Bible known as one of King Saul’s daughters in the early monarchy of ancient Israel.
-
D.
Merkheuli
Merkheuli is a village in Abkhazia, Georgia, historically notable as the birthplace of Soviet security chief Lavrentiy Beria.
-
E.
Khvanchkara
Khvanchkara is a renowned semi-sweet red wine from Georgia, celebrated for its rich, fruity character and traditional production in the Racha region.
- 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_69bd445d94788190b72e2cc563120995 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd78daab708190a42734a14dddb2fc |
completed | March 20, 2026, 4:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed0099afc8190badca81bd5efb8f6 |
completed | March 21, 2026, 5:06 p.m. |
| NEDg | Description generation | batch_69bed3f4af288190beec97356b21f990 |
completed | March 21, 2026, 5:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bed49625688190972acb1cb0c2a83b |
completed | March 21, 2026, 5:25 p.m. |
Created at: March 20, 2026, 1:44 p.m.