Triple
T11681027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhaca |
E277613
|
entity |
| Predicate | hasLanguageVariety |
P5595
|
FINISHED |
| Object | IsiBhaca |
E277613
|
NE 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: IsiBhaca | Statement: [Bhaca, hasLanguageVariety, IsiBhaca]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IsiBhaca Context triple: [Bhaca, hasLanguageVariety, IsiBhaca]
-
A.
Bhaca
chosen
Bhaca are a Xhosa-related ethnic group of South Africa known for their distinct language variety, cultural traditions, and historical chiefdoms in the Eastern Cape region.
-
B.
Pakpak Keppas
Pakpak Keppas is a regional dialect of the Pakpak Dairi language spoken by the Pakpak ethnic community in parts of North Sumatra, Indonesia.
-
C.
Rancaekek
Rancaekek is a suburban district in West Java, Indonesia, known as a growing residential and industrial area on the eastern outskirts of Bandung.
-
D.
Tagakaulo
Tagakaulo are an indigenous ethnic group in the southern Philippines, traditionally inhabiting parts of Mindanao and known for their distinct language and cultural practices.
-
E.
Carakan
Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a461b0908190bef4e1c6777affcf |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef141134bc81908c0cfb0a3711c115 |
completed | April 27, 2026, 7:45 a.m. |
Created at: April 8, 2026, 9:40 p.m.