Triple
T6672195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дьокуускай |
E151756
|
entity |
| Predicate | buildingFoundationType |
P29685
|
FINISHED |
| Object | permafrost-adapted pile foundations |
—
|
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: permafrost-adapted pile foundations | Statement: [Дьокуускай, buildingFoundationType, permafrost-adapted pile foundations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingFoundationType Context triple: [Дьокуускай, buildingFoundationType, permafrost-adapted pile foundations]
-
A.
foundationType
chosen
Indicates the structural or organizational basis on which something is built, established, or supported.
-
B.
buildingType
Indicates the specific category or function that characterizes what kind of building something is.
-
C.
constructionType
Indicates the specific method or style by which something is built or constructed.
-
D.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an entity.
-
E.
originalFoundationType
Indicates the type or nature of the initial foundational structure or base on which something was first established or built.
- 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_69c687f71fc081909dbd45d6377f6045 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce738fe88190a5557900efeec7ec |
completed | March 27, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69c6ad09974c81908784300ae218961f |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:03 p.m.