Triple
T12898717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madytos |
E308560
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Byzantine town |
C6165
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Byzantine town Context triple: [Madytos, instanceOf, Byzantine town]
-
A.
Byzantine city
chosen
A Byzantine city is an urban center of the Eastern Roman (Byzantine) Empire characterized by fortified walls, Christian religious institutions, administrative and commercial hubs, and a blend of Greco-Roman and Eastern cultural influences.
-
B.
Roman town
A Roman town is an urban settlement in the Roman Empire characterized by planned streets, public buildings such as forums, baths, and temples, and a structured social and administrative organization under Roman law and culture.
-
C.
Phrygian city
A Phrygian city is an ancient urban settlement located in the historical region of Phrygia in central Anatolia, characterized by its distinctive rock-cut architecture, religious monuments, and role in the Phrygian kingdom’s political and cultural life.
-
D.
ancient ruined city
An ancient ruined city is a long-abandoned urban settlement whose remaining structures, artifacts, and landscape features reveal the remnants of a once-thriving civilization now decayed by time and nature.
-
E.
medieval city
A medieval city is a densely populated, fortified urban center characterized by narrow winding streets, defensive walls, a central marketplace, religious and administrative buildings, and distinct social and economic quarters.
- F. None of above.
Provenance (1 batch)
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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
Created at: April 9, 2026, 5:40 p.m.