Triple
T24690008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leszno Plateau |
E611407
|
entity |
| Predicate | formsLandscapeAround |
P75369
|
FINISHED |
| Object | Leszno |
—
|
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: Leszno | Statement: [Leszno Plateau, formsLandscapeAround, Leszno]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsLandscapeAround Context triple: [Leszno Plateau, formsLandscapeAround, Leszno]
-
A.
formsLandscapeWith
Indicates that one entity combines or interacts with another to create or constitute a particular landscape or environmental formation.
-
B.
formsAround
chosen
Indicates that one entity develops or shapes itself so as to encircle, surround, or be organized around another entity.
-
C.
formsNear
Indicates that one entity takes shape or comes into existence in close spatial proximity to another entity.
-
D.
formsFocalPointOf
Indicates that something serves as the central or primary point of attention, interest, or activity within a given context or arrangement.
-
E.
formsIn
Indicates that one entity takes shape, develops, or comes into existence within or inside 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_69e2c4d678b081908910f4271627a31a |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f410fe3b848190ae296a29f742ee30 |
completed | May 1, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f40ee8ada8819089a7016b50308ff0 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 3:20 a.m.