Triple
T8136748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chufut-Kale |
E189990
|
entity |
| Predicate | earlierName |
P65
|
FINISHED |
| Object |
Kyrk-Or (Kirkor)
Kyrk-Or (Kirkor) is the historical Crimean Tatar name for the medieval cave town and fortress now known as Chufut-Kale in Crimea.
|
E714245
|
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: Kyrk-Or (Kirkor) | Statement: [Chufut-Kale, earlierName, Kyrk-Or (Kirkor)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kyrk-Or (Kirkor) Context triple: [Chufut-Kale, earlierName, Kyrk-Or (Kirkor)]
-
A.
Kirovakan
Kirovakan is the former name of Vanadzor, a major industrial city in northern Armenia.
-
B.
Kerkebet
Kerkebet is a small town in the Anseba region of Eritrea.
-
C.
Evinayong
Evinayong is a town in mainland Equatorial Guinea that serves as an important local administrative and commercial center.
-
D.
Surp Hreşdagabet Armenian Church
Surp Hreşdagabet Armenian Church is a historic Armenian Apostolic church located in Istanbul’s Balat district, known for serving the local Armenian community.
-
E.
Ayvansaray
Ayvansaray is a historic neighborhood on the Golden Horn in Istanbul, known for its old city walls, traditional wooden houses, and rich Byzantine and Ottoman heritage.
- 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: Kyrk-Or (Kirkor) Triple: [Chufut-Kale, earlierName, Kyrk-Or (Kirkor)]
Generated description
Kyrk-Or (Kirkor) is the historical Crimean Tatar name for the medieval cave town and fortress now known as Chufut-Kale in Crimea.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kyrk-Or (Kirkor) Target entity description: Kyrk-Or (Kirkor) is the historical Crimean Tatar name for the medieval cave town and fortress now known as Chufut-Kale in Crimea.
-
A.
Kirovakan
Kirovakan is the former name of Vanadzor, a major industrial city in northern Armenia.
-
B.
Kerkebet
Kerkebet is a small town in the Anseba region of Eritrea.
-
C.
Evinayong
Evinayong is a town in mainland Equatorial Guinea that serves as an important local administrative and commercial center.
-
D.
Surp Hreşdagabet Armenian Church
Surp Hreşdagabet Armenian Church is a historic Armenian Apostolic church located in Istanbul’s Balat district, known for serving the local Armenian community.
-
E.
Ayvansaray
Ayvansaray is a historic neighborhood on the Golden Horn in Istanbul, known for its old city walls, traditional wooden houses, and rich Byzantine and Ottoman heritage.
- F. None of above. chosen
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_69ca82bd9900819099477cdc2eb4244f |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb440171d48190afa4a312ab19389c |
completed | March 31, 2026, 3:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc949d9c7c81908efb4880f9250166 |
completed | April 1, 2026, 3:44 a.m. |
| NEDg | Description generation | batch_69cc9605b8248190a621ea934c58913d |
completed | April 1, 2026, 3:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc970cf55c8190abf432ac68d6bbc3 |
completed | April 1, 2026, 3:54 a.m. |
Created at: March 30, 2026, 5:35 p.m.