Triple
T15913592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salzwedel |
E385908
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Gusev |
E823634
|
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: Gusev | Statement: [Salzwedel, hasTwinTown, Gusev]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gusev Context triple: [Salzwedel, hasTwinTown, Gusev]
-
A.
Gusev
chosen
Gusev is a town in Russia’s Kaliningrad Oblast, near the border with Poland, known for its historical ties to East Prussia and cross-border regional cooperation.
-
B.
Gusev crater
Gusev crater is a large impact crater on Mars that was explored by NASA’s Spirit rover in search of past water-related geological activity.
-
C.
Mirny
Mirny is a remote mining town in eastern Siberia best known for its massive open-pit diamond mine and role in Russia’s diamond industry.
-
D.
Mirny Station
Mirny Station is a Russian research base in Antarctica that serves as a key hub for scientific studies of the polar environment and climate.
-
E.
Kozhedub
Kozhedub is a Slavic surname most famously borne by Ivan Kozhedub, a highly decorated Soviet World War II fighter ace.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e15661046c819097a53de2a3e0443b |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb0592b5c8190a4597644864a6bcb |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.