Triple
T15216192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | White Sea coast |
E363641
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Kem |
E852187
|
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: Kem | Statement: [White Sea coast, hasPort, Kem]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kem Context triple: [White Sea coast, hasPort, Kem]
-
A.
Kem
chosen
Kem is a historic town and seaport in northern Russia on the White Sea, long associated with Pomor seafaring and trade.
-
B.
KEM
KEM is the National Rail station code for Kemble railway station in Gloucestershire, England.
-
C.
KEM
KEM is the IATA airport code for Kemi-Tornio Airport in northern Finland.
-
D.
Kiesen
Kiesen is a municipality in the canton of Bern, Switzerland, served by a station on the Bern–Thun railway line.
-
E.
Kaje
Kaje is an exonym used to refer to the Bajju people, an ethnic group primarily found in Kaduna State, Nigeria.
- 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0076f90c481909989befe031a2cae |
completed | April 15, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fed343f51481908f04c35d37b39ad2 |
completed | May 9, 2026, 6:25 a.m. |
Created at: April 10, 2026, 3:11 a.m.