Triple
T22082577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wuming dialect |
E545687
|
entity |
| Predicate | hasAncestor |
P369
|
FINISHED |
| Object | Proto-Tai |
—
|
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: Proto-Tai | Statement: [Wuming dialect, hasAncestor, Proto-Tai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Proto-Tai Context triple: [Wuming dialect, hasAncestor, Proto-Tai]
-
A.
Proto-Tai
chosen
Proto-Tai is the reconstructed common ancestor language of the Tai language family, from which modern Tai languages such as Thai and Lao ultimately developed.
-
B.
Proto-Austro-Tai
Proto-Austro-Tai is a hypothetical ancestral language proposed to underlie both the Austronesian and Tai-Kadai language families within the Austro-Tai hypothesis.
-
C.
Proto-Kam–Tai
Proto-Kam–Tai is the reconstructed common ancestor language of the Kam–Tai (Kra–Dai) language branch, from which Central Tai and related languages are derived.
-
D.
Proto-Nahuan
Proto-Nahuan is the reconstructed common ancestor language of the Nahuan (including Nahuatl) language family of Mesoamerica.
-
E.
Proto-Tungusic
Proto-Tungusic is the reconstructed common ancestor of the Tungusic language family, from which languages like Hezhen are believed to have descended.
- 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_69e11e3523488190badd54b5d580c00d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128b706288190945c0c37e5ff2756 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.