Triple
T27359535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue de Berri |
E685781
|
entity |
| Predicate | upscaleArea |
P37114
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Rue de Berri, upscaleArea, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upscaleArea Context triple: [Rue de Berri, upscaleArea, true]
-
A.
floorAreaIncrease
Indicates an increase in the total floor area of a space, building, or structure compared to a previous state or reference.
-
B.
isUpscale
Indicates that something possesses a high-end, luxurious, or premium quality or status compared to typical or standard options.
-
C.
isInUpscaleNeighborhood
chosen
Indicates that the subject is located within a neighborhood characterized by higher property values, amenities, and socioeconomic status compared to typical areas.
-
D.
areaScale
Indicates a proportional relationship where one area value is a scaled (enlarged or reduced) version of another by a specific factor.
-
E.
largerScaleAlternative
Indicates that one option represents a broader, more extensive, or higher-level version of another option, serving as its larger-scale alternative.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62c21405c81909c486d3b9d9be274 |
completed | May 2, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:53 a.m.