Triple
T19828054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Bridge in Vilnius |
E476379
|
entity |
| Predicate | hasNameInRussian |
P20560
|
FINISHED |
| Object | Зелёный мост |
—
|
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: Зелёный мост | Statement: [Green Bridge in Vilnius, hasNameInRussian, Зелёный мост]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Зелёный мост Context triple: [Green Bridge in Vilnius, hasNameInRussian, Зелёный мост]
-
A.
Зелёный мост
chosen
Зелёный мост — это исторический пешеходный мост в центре Санкт-Петербурга, перекинутый через реку Мойку и известный своим характерным зелёным цветом.
-
B.
Золотой мост
Золотой мост — это вантовый мост во Владивостоке, являющийся одной из главных архитектурных достопримечательностей города и важной транспортной артерией.
-
C.
Mittlere Brücke
Mittlere Brücke is a historic stone bridge over the Rhine in Basel, Switzerland, and one of the city’s most iconic landmarks.
-
D.
The Green
The Green is a small rural settlement in Cumbria, England, situated near the town of Millom in the southwestern Lake District area.
-
E.
The Green
The Green is a historic central park and community gathering space located in downtown Morristown, New Jersey.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656cc0f2c81908137caa4c2087027 |
completed | April 20, 2026, 4:39 p.m. |
Created at: April 10, 2026, 1:50 p.m.