Triple
T18986218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Praça de D. Pedro IV |
E464564
|
entity |
| Predicate | pavementStyle |
P58826
|
FINISHED |
| Object | black and white limestone mosaic |
—
|
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 limestone mosaic | Statement: [Praça de D. Pedro IV, pavementStyle, black and white limestone mosaic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pavementStyle Context triple: [Praça de D. Pedro IV, pavementStyle, black and white limestone mosaic]
-
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.
streetMaterial
Indicates the material composition from which a street or road surface is made.
-
D.
pavementStyleIntroduced
Indicates that a particular pavement style was first implemented or brought into use in relation to another entity (such as a place, project, or time period).
-
E.
pavedBy
Indicates that a surface, route, or area has been covered or constructed with a hard material by a specified agent or process.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d660835c8190bedd78590b3e0a7e |
completed | April 20, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.