Triple
T21451090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skáli |
E529207
|
entity |
| Predicate | traditionalRoofType |
P78546
|
FINISHED |
| Object | turf roofs |
—
|
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: turf roofs | Statement: [Skáli, traditionalRoofType, turf roofs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalRoofType Context triple: [Skáli, traditionalRoofType, turf roofs]
-
A.
roofTypeTypical
Indicates that a specified roof type is the common or characteristic roof style typically found for a given context or entity.
-
B.
hasTypeOfRoof
chosen
Indicates that an entity possesses or is characterized by a specific kind or style of roof.
-
C.
roofMaterialTypical
Indicates the material that is most commonly or characteristically used for the roof of a given structure or building type.
-
D.
traditionallyBuiltOver
Indicates that one entity has been constructed on top of another in a manner consistent with long-established or customary building practices.
-
E.
roofMaterialOriginal
Indicates the material that was originally used to construct the roof of a structure.
- 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9d33e648190864b0ef5acf36659 |
completed | April 23, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69e631df1b38819088d3604854e697b4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:06 p.m.