Triple
T22986360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hauran |
E571616
|
entity |
| Predicate | majorCity |
P316
|
FINISHED |
| Object | Bosra |
—
|
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: Bosra | Statement: [Hauran, majorCity, Bosra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bosra Context triple: [Hauran, majorCity, Bosra]
-
A.
Bosra
chosen
Bosra is an ancient city in southern Syria renowned for its remarkably well-preserved Roman theater and layers of Nabataean, Roman, Byzantine, and Islamic architectural heritage.
-
B.
Ma'arrat al-Nu'man
Ma'arrat al-Nu'man is a historic town in northwestern Syria known as the birthplace of the medieval Arab poet and philosopher Al-Ma'arri.
-
C.
Dar el-Batha
Dar el-Batha is a former royal palace in Fez, Morocco, now serving as a museum renowned for its collection of traditional Moroccan arts and crafts.
-
D.
Ain al-Tamur
Ain al-Tamur is a town in central Iraq known for its date palm oases and historical sites, located within the Karbala Governorate.
-
E.
Zababdeh
Zababdeh is a predominantly Christian Palestinian town in the northern West Bank known as a local religious and educational center.
- 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_69e245b3c50481908bb3741ec9f40862 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182996ee08190ab74014ee7ecac2b |
completed | April 29, 2026, 4:01 a.m. |
Created at: April 17, 2026, 3:49 p.m.