Triple
T22569560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geba script |
E558042
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Naxi Dongba script |
—
|
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: Naxi Dongba script | Statement: [Geba script, relatedTo, Naxi Dongba script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naxi Dongba script Context triple: [Geba script, relatedTo, Naxi Dongba script]
-
A.
Dongba script
chosen
Dongba script is an ancient pictographic writing system traditionally used by Naxi priests in southwestern China for religious texts and rituals.
-
B.
Tangut script
The Tangut script is a complex, logographic writing system historically used by the Tangut people of the Western Xia dynasty in northwestern China.
-
C.
Tai Nüa script
The Tai Nüa script is an abugida used primarily by the Tai Nüa (Dai) people of China and Southeast Asia to write the Tai Nüa language.
-
D.
Zhuang script
The Zhuang script is a writing system used primarily to represent the Zhuang language, a major Tai language spoken in southern China.
-
E.
Tibetan script
Tibetan script is an abugida writing system historically used for the Tibetan language and various Himalayan languages, characterized by its distinctive stacked consonants and association with Buddhist literature.
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fac7db08190ba4660535571498d |
completed | April 29, 2026, 1:32 a.m. |
Created at: April 16, 2026, 8:52 p.m.