Triple
T199636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Ndebele |
E4072
|
entity |
| Predicate | countryStatusInZimbabwe |
P8041
|
FINISHED |
| Object | recognized indigenous language |
—
|
LITERAL 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: recognized indigenous language | Statement: [Northern Ndebele, countryStatusInZimbabwe, recognized indigenous language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryStatusInZimbabwe Context triple: [Northern Ndebele, countryStatusInZimbabwe, recognized indigenous language]
-
A.
countryWithOfficialStatus
Indicates that a country holds an official, legally recognized status in relation to the referenced entity.
-
B.
UNMemberState
Indicates that a country is a recognized member state of the United Nations.
-
C.
deFactoCountry
Indicates that an entity functions as a country in practice (exercises governmental control and autonomy) even if it lacks full formal or legal recognition as a sovereign state.
-
D.
countryDeJure
Indicates that one entity is the legally recognized (de jure) country having sovereignty or authority over another entity.
-
E.
countryType
Indicates the classification or category of a country based on a specified typology (e.g., political, economic, or geographic type).
- F. None of above. chosen
Provenance (4 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_69a254bca59881909a15e1496f1508c7 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a25bcc6dc88190b8c24b485588dfe4 |
completed | Feb. 28, 2026, 3:06 a.m. |
| PD | Predicate disambiguation | batch_69a25b4886b48190b46fd2244648a098 |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25bc6ba208190aa8bec59d32f95fd |
completed | Feb. 28, 2026, 3:06 a.m. |
Created at: Feb. 28, 2026, 2:44 a.m.