Triple
T23163705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chonan languages |
E578655
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Selk'nam language |
E1572787
|
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: Selk'nam language | Statement: [Chonan languages, hasMember, Selk'nam language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Selk'nam language Context triple: [Chonan languages, hasMember, Selk'nam language]
-
A.
Selk'nam language
chosen
The Selk'nam language is an extinct Chonan language once spoken by the Selk'nam (Ona) people of Tierra del Fuego in southern South America.
-
B.
Chukchi language
The Chukchi language is a Chukotko-Kamchatkan language spoken by the Indigenous Chukchi people of northeastern Siberia, Russia.
-
C.
Nanai language
Nanai language is a critically endangered Tungusic language spoken by the Nanai people of the Russian Far East and northeastern China.
-
D.
Selkup language
The Selkup language is a critically endangered Uralic (Samoyedic) language spoken by the indigenous Selkup people of western Siberia in Russia.
-
E.
Yugtun
Yugtun is the Central Alaskan Yup’ik language spoken by Yup’ik people in western and southwestern Alaska.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f29be30819091e18551044a98f3 |
completed | April 29, 2026, 4:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3f428730819093c8c29d2f5b2c2a |
completed | May 19, 2026, 10:45 a.m. |
Created at: April 17, 2026, 4:02 p.m.