Triple
T16829591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ardahan Castle |
E409112
|
entity |
| Predicate | overlooks |
P1323
|
FINISHED |
| Object | Ardahan city |
E84141
|
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: Ardahan city | Statement: [Ardahan Castle, overlooks, Ardahan city]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ardahan city Context triple: [Ardahan Castle, overlooks, Ardahan city]
-
A.
Ardahan
chosen
Ardahan is a town in northeastern Turkey that serves as the capital of Ardahan Province near the border with Georgia.
-
B.
Trabzon
Trabzon is a historic city in northeastern Turkey that serves as a major Black Sea port and regional cultural and commercial center.
-
C.
Karabük
Karabük is an industrial city in northern Turkey best known for its historic iron and steel industry and its proximity to the UNESCO-listed Ottoman town of Safranbolu.
-
D.
Adapazarı
Adapazarı is a city in northwestern Turkey that serves as the administrative center of Sakarya Province and is known for its agricultural production and regional commerce.
-
E.
Suşehri
Suşehri is a town and district in northeastern Turkey known for its location within Sivas Province and its surrounding mountainous landscape.
- 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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b315dbbc81908a1c83069e058770 |
completed | April 18, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2a08ac8819098e7094ee5ce4ed5 |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:23 a.m.