Triple
T10547164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saba |
E248850
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Sabaic |
E68213
|
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: Sabaic | Statement: [Saba, hasLanguage, Sabaic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sabaic Context triple: [Saba, hasLanguage, Sabaic]
-
A.
Sabaic
chosen
Sabaic is an ancient South Arabian Semitic language once used in inscriptions and documents in what is now Yemen.
-
B.
Sabaot
Sabaot is a Southern Nilotic language spoken primarily by the Sabaot people in the Mount Elgon region of Kenya and Uganda.
-
C.
Sabaot language
The Sabaot language is a Nilotic language spoken by the Sabaot people of western Kenya and eastern Uganda, closely associated with the Kalenjin language cluster.
-
D.
Basaa
Basaa is a Bantu language spoken primarily by the Basaa people in Cameroon.
-
E.
Abasa
Abasa is the 80th chapter of the Qur'an, known for its admonition regarding a moment when the Prophet Muhammad frowned at a blind man seeking guidance.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d526d20ef48190ab9f70d4ce5f2a11 |
completed | April 7, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9344a53fc81909765061d07d0cd20 |
completed | April 10, 2026, 5:32 p.m. |
Created at: April 6, 2026, 12:33 p.m.