Triple
T16351573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tusheti |
E397072
|
entity |
| Predicate | hasAdministrativeCenter |
P1474
|
FINISHED |
| Object | Omalo |
E1176670
|
NE FINISHED |
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: Omalo | Statement: [Tusheti, hasAdministrativeCenter, Omalo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Omalo Context triple: [Tusheti, hasAdministrativeCenter, Omalo]
-
A.
Omalo
chosen
Omalo is a remote mountain village in northeastern Georgia, known as the main gateway to the historic Tusheti region in the Greater Caucasus.
-
B.
Elmolo
Elmolo is a small Indigenous ethnic group living along the shores of Lake Turkana in northern Kenya, traditionally known for their fishing-based culture and Cushitic language.
-
C.
Mokuola
Mokuola is a small, lush island in Hilo Bay on Hawaii’s Big Island, known for its tranquil park, tidal pools, and scenic views of the bay and Mauna Kea.
-
D.
Looma
Looma is an alternative name for Loma, which may refer to various places, peoples, or entities sharing that designation.
-
E.
Malaeloa
Malaeloa is a village in American Samoa located within Tualauta County on the island of Tutuila.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2facbf60c8190aa47d4c45ff59354 |
completed | April 18, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002db6375c81908c64dbe2bc987b1a |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:07 a.m.