Triple
T36232723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mississippi River at Muscatine |
E891291
|
entity |
| Predicate | hasOppositeBank |
P175559
|
FINISHED |
| Object | Illinois (east) bank |
—
|
LITERAL 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: Illinois (east) bank | Statement: [Mississippi River at Muscatine, hasOppositeBank, Illinois (east) bank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOppositeBank Context triple: [Mississippi River at Muscatine, hasOppositeBank, Illinois (east) bank]
-
A.
isOppositeBankOf
chosen
Indicates that one entity is located on the bank of a river or similar water body directly across from the bank where the other entity is located.
-
B.
oppositeBankHasPart
Indicates that a bank of a river or similar feature includes, as a component or segment, the bank located on the opposite side.
-
C.
oppositeBankCountry
Indicates that two entities are located on opposing banks of the same river or waterway, each in a different country.
-
D.
hasOppositeBankStreet
Indicates that a street is located on the opposite bank of a river or waterway relative to another street.
-
E.
oppositeBankCity
Indicates that one city is located on the opposite bank of a river from another city.
- 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_69f76e4387048190a1b27bcbf4ec7423 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: May 3, 2026, 4:09 p.m.