Triple
T1879321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donbas |
E39814
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Mariupol |
E54211
|
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: Mariupol | Statement: [Donbas, hasCity, Mariupol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mariupol Context triple: [Donbas, hasCity, Mariupol]
-
A.
Mariupol
chosen
Mariupol is a major industrial city in southeastern Ukraine known for its strategic port on the Sea of Azov and its significant role in recent military conflicts.
-
B.
Kramatorsk
Kramatorsk is an industrial city in eastern Ukraine that has become a key administrative and strategic center in the Donbas region.
-
C.
Donetsk
Donetsk is a major industrial city in eastern Ukraine, historically known for its coal mining and steel production.
-
D.
Mykolaiv
Mykolaiv is a major shipbuilding and industrial city in southern Ukraine located near the Black Sea.
-
E.
Kharkiv
Kharkiv is Ukraine’s second-largest city and a major industrial, cultural, and educational center in the northeast of the country.
- 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_69a88633e4fc8190b7eb40463e048ec5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb0f8e9f08190a210440823fad69e |
completed | March 7, 2026, 5 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3a777a481909e8b350811ee29c0 |
completed | March 9, 2026, 11:48 a.m. |
Created at: March 4, 2026, 7:34 p.m.