Triple
T3252458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Modern South Arabian languages |
E68212
|
entity |
| Predicate | languageFamilyDivision |
P35117
|
FINISHED |
| Object |
Western Modern South Arabian
Western Modern South Arabian is a subgroup of the Modern South Arabian languages spoken in parts of Yemen and Oman, characterized by distinct Semitic linguistic features separate from Arabic.
|
E68212
|
NE FINISHED |
How this triple was built (4 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: Western Modern South Arabian | Statement: [Modern South Arabian languages, languageFamilyDivision, Western Modern South Arabian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Western Modern South Arabian Context triple: [Modern South Arabian languages, languageFamilyDivision, Western Modern South Arabian]
-
A.
Old South Arabian
Old South Arabian is an extinct group of ancient Semitic languages once spoken in what is now Yemen and surrounding regions, known primarily from inscriptions written in a distinctive consonantal script.
-
B.
Modern South Arabian languages
Modern South Arabian languages are a small group of endangered Semitic languages spoken primarily in Yemen and Oman, distinct from both Arabic and the ancient South Arabian languages.
-
C.
Safaitic Arabic
Safaitic Arabic is an ancient North Arabian dialect known from inscriptions left by nomadic tribes in the southern Syrian and northern Arabian deserts during the first centuries CE.
-
D.
South Arabian script
The South Arabian script is an ancient consonantal writing system used in the southern Arabian Peninsula, notably by the Sabaean and related cultures, and is a distinct branch of the early Semitic alphabets.
-
E.
Western Desert language
Western Desert language is a large group of closely related Australian Aboriginal languages spoken across central and western Australia, including varieties such as Yankunytjatjara and Pitjantjatjara.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Western Modern South Arabian Triple: [Modern South Arabian languages, languageFamilyDivision, Western Modern South Arabian]
Generated description
Western Modern South Arabian is a subgroup of the Modern South Arabian languages spoken in parts of Yemen and Oman, characterized by distinct Semitic linguistic features separate from Arabic.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Western Modern South Arabian Target entity description: Western Modern South Arabian is a subgroup of the Modern South Arabian languages spoken in parts of Yemen and Oman, characterized by distinct Semitic linguistic features separate from Arabic.
-
A.
Old South Arabian
Old South Arabian is an extinct group of ancient Semitic languages once spoken in what is now Yemen and surrounding regions, known primarily from inscriptions written in a distinctive consonantal script.
-
B.
Modern South Arabian languages
chosen
Modern South Arabian languages are a small group of endangered Semitic languages spoken primarily in Yemen and Oman, distinct from both Arabic and the ancient South Arabian languages.
-
C.
Safaitic Arabic
Safaitic Arabic is an ancient North Arabian dialect known from inscriptions left by nomadic tribes in the southern Syrian and northern Arabian deserts during the first centuries CE.
-
D.
South Arabian script
The South Arabian script is an ancient consonantal writing system used in the southern Arabian Peninsula, notably by the Sabaean and related cultures, and is a distinct branch of the early Semitic alphabets.
-
E.
Western Desert language
Western Desert language is a large group of closely related Australian Aboriginal languages spoken across central and western Australia, including varieties such as Yankunytjatjara and Pitjantjatjara.
- F. None of above.
Provenance (5 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf440bb88190a2450405afae7f1f |
completed | March 8, 2026, 5:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b28ec4375881908d7f22ef4a80b60c |
completed | March 12, 2026, 10 a.m. |
| NEDg | Description generation | batch_69b28fbaa3048190b42991ede51c6ca8 |
completed | March 12, 2026, 10:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2ab2315ec8190b27da4e41696a7e3 |
completed | March 12, 2026, 12:01 p.m. |
Created at: March 8, 2026, 3:09 p.m.