Triple
T22384284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beylik of Saruhan |
E553354
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Manisa |
—
|
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: Manisa | Statement: [Beylik of Saruhan, capital, Manisa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manisa Context triple: [Beylik of Saruhan, capital, Manisa]
-
A.
Manisa
chosen
Manisa is a historic city in western Turkey known for its agricultural production, especially grapes and olives, and its proximity to the Aegean coast.
-
B.
Isparta
Isparta is a city in southwestern Turkey known for its rose cultivation and production of rose oil and related products.
-
C.
Akhisar
Akhisar is a town in western Turkey that occupies the site of the ancient city of Thyatira, one of the early centers of Christianity in Asia Minor.
-
D.
Gedera
Gedera is a town in central Israel known for its agricultural roots and diverse immigrant communities.
-
E.
Bergama
Bergama is a town in western Turkey known for encompassing the archaeological remains of the ancient city of Pergamon, a major Hellenistic and Roman cultural and political 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1582e58dc8190a2ad6b10c9d1f951 |
completed | April 29, 2026, 1 a.m. |
Created at: April 16, 2026, 8:45 p.m.