Triple
T17588134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maria Kaczyńska |
E428377
|
entity |
| Predicate | placeOfDeath |
P21
|
FINISHED |
| Object | Smolensk |
—
|
NE NERFINISHED |
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: Smolensk | Statement: [Maria Kaczyńska, placeOfDeath, Smolensk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Smolensk Context triple: [Maria Kaczyńska, placeOfDeath, Smolensk]
-
A.
Smolensk
chosen
Smolensk is a historic city in western Russia near the Belarusian border, known for its strategic location and centuries-old fortifications.
-
B.
Podolsk
Podolsk is a major industrial city and former center of machine-building located just south of Moscow in western Russia.
-
C.
Smolenskaya
Smolenskaya is a Moscow Metro station on the Arbatsko–Pokrovskaya and Filyovskaya lines, located near the historic Arbat district.
-
D.
Borisoglebsk
Borisoglebsk is a small Russian city known for its historical architecture and location on the Vorona River in southwestern Russia.
-
E.
Trubchevsk
Trubchevsk is a historic town in western Russia, known as a former medieval center and namesake of the Principality of Trubchevsk.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469e50a80819098920d9190c30225 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 5:51 a.m.