Triple
T12352406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rome’s Piazza di Spagna area |
E294523
|
entity |
| Predicate | shoppingType |
P47325
|
FINISHED |
| Object | high-end fashion boutiques |
—
|
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: high-end fashion boutiques | Statement: [Rome’s Piazza di Spagna area, shoppingType, high-end fashion boutiques]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shoppingType Context triple: [Rome’s Piazza di Spagna area, shoppingType, high-end fashion boutiques]
-
A.
shopSpecialty
Indicates that a shop primarily focuses on or is specially known for offering a particular type of product or service.
-
B.
isShoppingStreet
Indicates that a location functions primarily as a street characterized by a concentration of shops and commercial retail activity.
-
C.
isShoppingDestination
chosen
Indicates that a place serves as a primary location where people go to shop for goods or services.
-
D.
hasShoppingMall
Indicates that one entity possesses, contains, or includes a shopping mall within its area or domain.
-
E.
buys
Indicates that one entity purchases or acquires something from another entity, typically in exchange for money or other compensation.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f8aa33c8190b22b7dff9559b8ed |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ecb5efc819086a3530282278bb1 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.