Triple
T3651905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Up on the Roof |
E77435
|
entity |
| Predicate | describesSetting |
P25484
|
FINISHED |
| Object | urban rooftop |
—
|
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: urban rooftop | Statement: [Up on the Roof, describesSetting, urban rooftop]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: describesSetting Context triple: [Up on the Roof, describesSetting, urban rooftop]
-
A.
settingDescription
chosen
Indicates the descriptive details or characteristics that define the context or environment in which something occurs.
-
B.
usedAsSettingFor
Indicates that one entity serves as the backdrop, location, or environment in which another entity (such as an event, story, or activity) takes place.
-
C.
featuresSetting
Indicates that something includes, presents, or highlights a particular setting as a notable or primary aspect.
-
D.
setting
Indicates the place, time, or context in which an event, action, or interaction occurs.
-
E.
notableSetting
Indicates that a particular place or environment is especially significant or prominent as the context in which an entity is situated or occurs.
- 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_69ad85def5cc8190863dccf55a18bebb |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3b664448190986b5223d59de282 |
completed | March 8, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69adb84650148190bf79231105e58d7f |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.