Triple
T13175667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derry & Toms |
E313091
|
entity |
| Predicate | roofGardensLocation |
P22557
|
FINISHED |
| Object | top of the Derry & Toms building |
—
|
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: top of the Derry & Toms building | Statement: [Derry & Toms, roofGardensLocation, top of the Derry & Toms building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roofGardensLocation Context triple: [Derry & Toms, roofGardensLocation, top of the Derry & Toms building]
-
A.
gardensLocation
Indicates that an entity engages in gardening activities at a specified location.
-
B.
roofGardenUse
Indicates that a roof garden is being utilized for a specific function or activity.
-
C.
gardensBuiltFor
Indicates that one entity (such as a garden or landscaped area) was created or designed specifically for the benefit, use, or purpose of another entity.
-
D.
rockGardenView
Indicates that an entity has a view overlooking or directly facing a rock garden.
-
E.
containsGarden
chosen
Indicates that one entity includes or has a garden within its area or boundaries.
- 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_69d806ac3ee081909b2fd27d060aa974 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bc2c0c88190be357811aa8e828d |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:14 p.m.