Triple
T20899361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuvinian language |
E514628
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Tofa language |
—
|
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: Tofa language | Statement: [Tuvinian language, closelyRelatedTo, Tofa language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tofa language Context triple: [Tuvinian language, closelyRelatedTo, Tofa language]
-
A.
Tofa language
chosen
Tofa is a critically endangered Turkic language traditionally spoken by the Tofa (Tofalars) people of south-central Siberia in Russia.
-
B.
Towa language
Towa is a Native American language spoken by the Towa (Jemez) people of New Mexico and is part of the Puebloan language family.
-
C.
Touo language
Touo is an Oceanic language spoken by a small community in the Solomon Islands, noted for its distinct phonology and limited number of speakers.
-
D.
Toundanow language
The Toundanow language is an Austronesian language spoken by the Tonsawang people of northern Sulawesi, Indonesia.
-
E.
Thaua language
The Thaua language is an Indigenous Australian Aboriginal language traditionally spoken by the Thaua (a group of the Yuin people) of the south coast of New South Wales.
- 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e8f92bd88190b59b2131ad1d9aa1 |
completed | April 21, 2026, 3:03 a.m. |
Created at: April 16, 2026, 12:47 p.m.