Triple
T10483073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalenjin |
E247219
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Omotik |
E247227
|
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: Omotik | Statement: [Kalenjin, closelyRelatedTo, Omotik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Omotik Context triple: [Kalenjin, closelyRelatedTo, Omotik]
-
A.
Omotik
chosen
Omotik is a critically endangered Southern Nilotic language spoken by a small community in Kenya.
-
B.
Otomí
Otomí is an indigenous people of central Mexico whose Oto-Manguean language and rich cultural traditions have persisted since pre-Hispanic times.
-
C.
Munirka
Munirka is a densely populated residential and commercial neighborhood in South Delhi, known for its urban village character, proximity to major institutions, and extensive rental housing.
-
D.
Oza
"Oza" is a prominent poetic work by Russian poet Andrei Voznesensky, reflecting his innovative style and experimental approach to verse.
-
E.
Tarusa
Tarusa is a small historic town in western Russia known for its scenic location on the Oka River and its associations with Russian artists and writers.
- 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_69d381c309b88190af78aa681cf6a4c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509678ac88190984f18a2162e2dcf |
completed | April 7, 2026, 1:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8a03c647c81909521fee4a66ec8ac |
completed | April 10, 2026, 7:01 a.m. |
Created at: April 6, 2026, 12:22 p.m.