Triple
T18305780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivry-sur-Seine |
E438478
|
entity |
| Predicate | adjacentRiverBank |
P39043
|
FINISHED |
| Object | left bank of the Seine |
—
|
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: left bank of the Seine | Statement: [Ivry-sur-Seine, adjacentRiverBank, left bank of the Seine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentRiverBank Context triple: [Ivry-sur-Seine, adjacentRiverBank, left bank of the Seine]
-
A.
riverBankOnOneSide
Indicates that a river flows adjacent to and borders only one side of a specified bank or land area.
-
B.
riverBankOnEastSide
Indicates that a river bank is located on the eastern side of a river or watercourse.
-
C.
riverBankOnUSSide
Indicates that the river bank being referred to is located on the United States side of the river.
-
D.
locatedOnBankOfRiver
chosen
Indicates that one entity is situated along or directly adjacent to the bank of a specified river.
-
E.
locatedAcrossRiverFrom
Indicates that one entity is situated on the opposite side of a river relative to another entity.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50183394081909b86cefaaa0a3aa8 |
completed | April 19, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69e44fdf43d08190bbcfb6b1fe3cc0ee |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:35 a.m.