Triple
T4133164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunhuang |
E85086
|
entity |
| Predicate | historicalLanguage |
P7165
|
FINISHED |
| Object | Tibetan |
E109616
|
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: Tibetan | Statement: [Dunhuang, historicalLanguage, Tibetan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tibetan Context triple: [Dunhuang, historicalLanguage, Tibetan]
-
A.
Tibetan
chosen
Tibetan is a Sino-Tibetan language spoken primarily in Tibet and surrounding Himalayan regions, serving as the liturgical language of Tibetan Buddhism and a key marker of Tibetan cultural identity.
-
B.
Dholuo
Dholuo is a Nilotic language spoken primarily by the Luo people of western Kenya and parts of Tanzania.
-
C.
Dzongkha
Dzongkha is a Sino-Tibetan language spoken primarily in Bhutan, where it serves as the national and administrative language.
-
D.
Chochenyo
Chochenyo is an indigenous Ohlone language traditionally spoken in the East Bay region of the San Francisco Bay Area in California.
-
E.
Gyel dialect
The Gyel dialect is a regional variety of the Berom language spoken by the Berom people of central Nigeria.
- 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_69aed935ccd881909dc61f81bcdb7a78 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02306d608190bf8945d560f87c21 |
completed | March 9, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b576c4c0888190be156d093ea11207 |
completed | March 14, 2026, 2:55 p.m. |
Created at: March 9, 2026, 3:43 p.m.