Triple
T14868174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stadthaus Zürich |
E349671
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Limmat river |
—
|
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: Limmat river | Statement: [Stadthaus Zürich, locatedNear, Limmat river]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Limmat river Context triple: [Stadthaus Zürich, locatedNear, Limmat river]
-
A.
Limmat River
chosen
The Limmat River is a major Swiss waterway that flows out of Lake Zurich and runs through the city of Zurich before joining the Aare River.
-
B.
Esino River
The Esino River is a central Italian watercourse flowing through the Marche region to the Adriatic Sea, known for shaping the valleys and landscapes of the Umbrian-Marchigian Apennines.
-
C.
Rositsa River
Rositsa River is a river in central northern Bulgaria that flows through the Balkan foothills before joining the Yantra River.
-
D.
Lom River
The Lom River is a watercourse in northern Bulgaria that flows through the Danubian Plain before emptying into the Danube.
-
E.
Lom River
The Lom River is a waterway in central Cameroon that contributes to the Sanaga River system and supports surrounding ecosystems and local communities.
- 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_69d822ee4f408190b6ac3b2fa434f0df |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded5776b848190bfe3a06ff261dc31 |
completed | April 15, 2026, 12:01 a.m. |
Created at: April 10, 2026, 1:55 a.m.