Triple
T8992913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khotanese language |
E214832
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Saka language |
E122578
|
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: Saka language | Statement: [Khotanese language, closelyRelatedTo, Saka language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saka language Context triple: [Khotanese language, closelyRelatedTo, Saka language]
-
A.
Saka languages
chosen
The Saka languages are an extinct group of Eastern Iranian languages once spoken by the Saka (Scythian) peoples of Central Asia, including varieties such as Khotanese and Tumshuqese.
-
B.
Sakizaya language
The Sakizaya language is an indigenous Austronesian language spoken by the Sakizaya people of eastern Taiwan.
-
C.
Sakao language
The Sakao language is an Oceanic language spoken on Espiritu Santo Island in Vanuatu, known for its complex phonology and rich system of verbal morphology.
-
D.
Soga language
The Soga language is a Bantu language spoken primarily by the Basoga people in eastern Uganda.
-
E.
Mikasuki language
The Mikasuki language is a Native American Muskogean language traditionally spoken by the Miccosukee and Seminole peoples of Florida.
- 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_69ca83a05c608190bdfdbdb25e994b39 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6876583081909d936dc3c3152587 |
completed | April 1, 2026, 12:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd0cd2b948190947a26fe11ad81bf |
completed | April 3, 2026, 2:38 p.m. |
Created at: March 30, 2026, 7:04 p.m.