Triple
T2275817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky Mirror |
E50766
|
entity |
| Predicate | installationSiteType |
P3054
|
FINISHED |
| Object | theatre forecourt |
—
|
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: theatre forecourt | Statement: [Sky Mirror, installationSiteType, theatre forecourt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: installationSiteType Context triple: [Sky Mirror, installationSiteType, theatre forecourt]
-
A.
typeOfInstallation
Indicates the specific kind or category of installation associated with an entity (e.g., how or in what form something is installed).
-
B.
installedAt
chosen
Indicates that something has been set up, placed, or put into operation at a specific location or site.
-
C.
installationMedia
Indicates that something serves as or is used as the medium (such as a disk, image, or package) through which a software or system is installed.
-
D.
deploymentType
Indicates the manner or configuration in which a system, application, or component is deployed or made operational.
-
E.
installedBy
Indicates that one entity was set up, put in place, or made operational through the actions or intervention of another entity.
- 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_69a88b05910c8190a9a2b1ff230c85f9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc39c6ff0819081a07696f1c29990 |
completed | March 7, 2026, 6:20 a.m. |
| PD | Predicate disambiguation | batch_69abbdb7719081909143efa8f48df4e4 |
completed | March 7, 2026, 5:55 a.m. |
Created at: March 4, 2026, 7:48 p.m.