Triple
T14364817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Çankırı |
E356203
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object | Gangra |
E877565
|
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: Gangra | Statement: [Çankırı, formerName, Gangra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gangra Context triple: [Çankırı, formerName, Gangra]
-
A.
Gangra
chosen
Gangra is an ancient city in Paphlagonia, in what is now north-central Turkey, historically significant as a regional administrative and ecclesiastical center.
-
B.
Gangi
Gangi is a historic hilltop town in Sicily, Italy, renowned for its medieval architecture and picturesque views over the Madonie mountains.
-
C.
Ragiwara
Ragiwara is a residential neighborhood located within Lyari Town in Karachi, Pakistan.
-
D.
Igaliku
Igaliku is a small, historic settlement in southern Greenland known for its scenic fjord landscape and nearby Norse ruins.
-
E.
Gorikai
Gorikai is a central sacred text of the Japanese Konkokyo religion, containing the teachings and revelations of its founder.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8fad48748190a0f34ca4d02f9a3c |
completed | April 14, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c4cb0c4819094d59b4b1d43588b |
completed | May 8, 2026, 2:37 a.m. |
Created at: April 10, 2026, 1:15 a.m.