Triple
T32857046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hejin |
E840402
|
entity |
| Predicate | hasRiverTerraceLandforms |
P185672
|
FINISHED |
| Object | Fen River terraces |
—
|
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: Fen River terraces | Statement: [Hejin, hasRiverTerraceLandforms, Fen River terraces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRiverTerraceLandforms Context triple: [Hejin, hasRiverTerraceLandforms, Fen River terraces]
-
A.
riverineLocation
Indicates that something is located in, along, or directly associated with a river or river system.
-
B.
hasRiver
Indicates that a location or area contains, is traversed by, or is directly associated with a river.
-
C.
hasRiverBedType
Indicates the type or classification of the riverbed associated with a given river or watercourse.
-
D.
shapedByRiver
Indicates that something’s form, structure, or boundaries have been created or significantly modified by the action or influence of a river.
-
E.
hasRiverValleyType
Indicates that an entity (such as a river or geographic area) is characterized by or associated with a specific type of river valley.
- F. None of above. chosen
Provenance (4 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f7c33d59808190b647989a093f3488 |
completed | May 3, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b6e7a881908deb96bedb2713f4 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c29cf36481908e472d4dcb5573b9 |
completed | May 3, 2026, 9:48 p.m. |
Created at: May 1, 2026, 1:17 a.m.