Triple
T36295393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue Saint-Placide |
E893346
|
entity |
| Predicate | isPartOfRightBankOrLeftBank |
P95833
|
FINISHED |
| Object | Left Bank of Paris |
—
|
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: Left Bank of Paris | Statement: [Rue Saint-Placide, isPartOfRightBankOrLeftBank, Left Bank of Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfRightBankOrLeftBank Context triple: [Rue Saint-Placide, isPartOfRightBankOrLeftBank, Left Bank of Paris]
-
A.
hasCityOnRightBank
Indicates that a city is located on the right bank of a specified river or watercourse.
-
B.
locatedOnRightBank
Indicates that one entity is situated on the right bank (right side) of a river or similar watercourse relative to its direction of flow.
-
C.
hasCountryOnLeftBank
Indicates that a specified country is located on the left bank of a given river or waterway.
-
D.
isOnLeftBank
chosen
Indicates that one entity is located on the left bank (left side) of a river or similar waterway relative to its flow direction.
-
E.
hasCountryOnRightBank
Indicates that a specified country is located on the right bank of a given river or watercourse.
- F. None of above.
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_69f76e4a61f0819084a2b68dbbb4efc6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffc3f0b19c8190b5a749bc3cad21dd |
completed | May 9, 2026, 11:32 p.m. |
| PD | Predicate disambiguation | batch_69ffc1b882808190932b2d43ea5537c9 |
completed | May 9, 2026, 11:22 p.m. |
Created at: May 3, 2026, 4:09 p.m.