Triple
T22569462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naxi people |
E558040
|
entity |
| Predicate | script |
P505
|
FINISHED |
| Object | Geba 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: Geba script | Statement: [Naxi people, script, Geba script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geba script Context triple: [Naxi people, script, Geba script]
-
A.
Geba script
chosen
The Geba script is a traditional syllabic writing system used primarily by the Naxi people of southwestern China to record their language and cultural texts.
-
B.
Ruqʿah script
Ruqʿah script is a simple, highly legible Arabic handwriting style commonly used for everyday writing and official documents in the Arab world.
-
C.
Xibe script
The Xibe script is a vertical alphabetic writing system used primarily for the Xibe language in China, derived from and closely resembling the traditional Manchu script.
-
D.
Tigalari script
The Tigalari script is a historical South Indian writing system used primarily to write Tulu and Sanskrit, closely related to other southern Brahmic scripts.
-
E.
Geba script used as syllabary
The Geba script used as a syllabary is a traditional writing system employed by the Naxi people to phonetically represent their language.
- 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.