Triple
T14021140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terrazza Mascagni |
E337331
|
entity |
| Predicate | pavingPattern |
P58826
|
FINISHED |
| Object | black-and-white checkerboard |
—
|
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: black-and-white checkerboard | Statement: [Terrazza Mascagni, pavingPattern, black-and-white checkerboard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pavingPattern Context triple: [Terrazza Mascagni, pavingPattern, black-and-white checkerboard]
-
A.
hasPavementPattern
chosen
Indicates that an entity possesses or is characterized by a specific pattern or design in its pavement surface.
-
B.
pavedWith
Indicates that a surface or area is covered or constructed using a specified material as its paving.
-
C.
glazingPattern
Indicates the arrangement or design pattern of glazing elements (such as panes or glass sections) within a structure or object.
-
D.
roofPatternInspiredBy
Indicates that the design or arrangement of a roof follows or is derived from a particular pattern, style, or source of inspiration.
-
E.
airingPattern
Indicates the recurring schedule or pattern according to which something (such as a program or content) is broadcast or made available.
- 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_69d81c6543a48190bd5ba93d7419e797 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2f3c7cd88190b236382058581740 |
completed | April 14, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69de05a802ac819090604025aae6a4d5 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:19 p.m.