Triple
T2162349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sogndalstrand |
E46828
|
entity |
| Predicate | hasPreservationPolicy |
P12561
|
FINISHED |
| Object | protected built environment |
—
|
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: protected built environment | Statement: [Sogndalstrand, hasPreservationPolicy, protected built environment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreservationPolicy Context triple: [Sogndalstrand, hasPreservationPolicy, protected built environment]
-
A.
preservationPolicy
chosen
Indicates the rules or strategy governing how something is maintained, protected, and retained over time.
-
B.
hasReferencePolicy
Indicates that an entity is governed by or associated with a specific reference policy that defines how it should be used, accessed, or managed.
-
C.
hasNotablePolicy
Indicates that an entity possesses a policy that is distinguished, significant, or otherwise noteworthy in its context.
-
D.
hasPolicyHistory
Indicates that an entity is associated with a record or sequence of past policies that have applied to it over time.
-
E.
hasVisitorPolicy
Indicates that an entity has an established policy governing the presence, behavior, or permissions of visitors.
- 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_69a88a184cbc8190877791f6552c2484 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe8b9c0881908373eabc7f81c394 |
completed | March 7, 2026, 5:58 a.m. |
| PD | Predicate disambiguation | batch_69abbd9c90408190b6b65498ca43ce26 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.