Triple
T23338407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pumi people |
E591663
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Pumi language |
—
|
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: Pumi language | Statement: [Pumi people, language, Pumi language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pumi language Context triple: [Pumi people, language, Pumi language]
-
A.
Pumi language
chosen
The Pumi language is a Sino-Tibetan language spoken primarily by the Pumi ethnic group in southwestern China, notable for its complex phonology and endangered status.
-
B.
Pomeranian language
The Pomeranian language is an extinct West Slavic tongue once spoken in the historical region of Pomerania along the Baltic Sea, closely related to Polish and Kashubian.
-
C.
Pokomo language
The Pokomo language is a Bantu language spoken primarily by the Pokomo people along Kenya’s Tana River.
-
D.
Puyuma language
The Puyuma language is an endangered Austronesian language spoken by the Puyuma Indigenous people of southeastern Taiwan.
-
E.
Umpila language
The Umpila language is an Indigenous Australian language traditionally spoken by the Umpila people of eastern Cape York Peninsula in Queensland.
- 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_69e25d20156c81908c5c53195bd9c738 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1983099188190a2e05cf81d62a641 |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:17 p.m.