Triple
T20709917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archaeopolis |
E509006
|
entity |
| Predicate | knownAs |
P39
|
FINISHED |
| Object | Tsikhegoji |
—
|
NE NERFINISHED |
How this triple was built (2 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: Tsikhegoji | Statement: [Archaeopolis, knownAs, Tsikhegoji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tsikhegoji Context triple: [Archaeopolis, knownAs, Tsikhegoji]
-
A.
Tsikhegoji
chosen
Tsikhegoji is a historical settlement that served as the capital of the medieval Georgian principality of Egrisi (Lazica) in western Georgia.
-
B.
Gegechkori
Gegechkori is the former name of the town now known as Martvili in western Georgia.
-
C.
Chakosi
Chakosi is a Gur language spoken primarily by the Chakosi (Anufo) people in parts of Ghana, Togo, and Benin.
-
D.
Chakvi
Chakvi is a small resort town on Georgia’s Black Sea coast, known for its subtropical climate, tea plantations, and proximity to Mtirala National Park.
-
E.
Chorokhi
Chorokhi is a river in the South Caucasus that flows from northeastern Turkey into southwestern Georgia before emptying into the Black Sea.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1974ba08190b0e5ad529be95e4c |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 12:14 p.m.