Triple
T2056018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prasun language |
E45675
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Ashkun language |
E45083
|
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: Ashkun language | Statement: [Prasun language, relatedTo, Ashkun language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ashkun language Context triple: [Prasun language, relatedTo, Ashkun language]
-
A.
Ashkun language
chosen
The Ashkun language is a Nuristani language spoken by the Ashkun people in remote regions of eastern Afghanistan.
-
B.
Avikam language
The Avikam language is a Kwa language spoken by the Avikam people of southern Côte d'Ivoire.
-
C.
Amuesha language
The Amuesha language, also known as Yanesha', is an Arawakan language spoken by the Yanesha' people of the central Peruvian Amazon.
-
D.
Khwarshi language
The Khwarshi language is a Northeast Caucasian (Nakh-Daghestanian) language spoken by a small ethnic group in Dagestan, Russia, known for its complex phonology and rich case system.
-
E.
Akebu language
The Akebu language is a Niger-Congo language spoken primarily by the Akebu people in parts of Togo and Ghana.
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9a9ce548190a5a3488fafb2e79e |
completed | March 7, 2026, 5:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae200eb09881908bbfe47ebb62f55e |
completed | March 9, 2026, 1:19 a.m. |
Created at: March 4, 2026, 7:40 p.m.