Triple
T11222606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shelton, Connecticut |
E265608
|
entity |
| Predicate | openSpacePolicy |
P97920
|
FINISHED |
| Object | active land preservation program |
—
|
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: active land preservation program | Statement: [Shelton, Connecticut, openSpacePolicy, active land preservation program]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openSpacePolicy Context triple: [Shelton, Connecticut, openSpacePolicy, active land preservation program]
-
A.
openSpaceType
Indicates the type or category of an open space associated with an entity (e.g., park, plaza, courtyard).
-
B.
isOpenSpace
Indicates that a given area or location is an unobstructed, accessible space rather than an enclosed or confined one.
-
C.
spacePolicy
Indicates a relationship where an entity establishes or adheres to rules, strategies, or guidelines governing activities and behavior in outer space.
-
D.
spacePolarity
Indicates a relationship where one entity’s spatial orientation, charge, or directional attribute is contrasted or opposed to another’s within a defined space.
-
E.
spaceType
Indicates the category or kind of physical or conceptual space associated with an entity.
- F. None of above. chosen
Provenance (4 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8ec8fb08190b27144ab65f85957 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d75cfbbb188190861efd5d94fe27da |
completed | April 9, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69d77062271c8190b63da714ab5beff9 |
completed | April 9, 2026, 9:24 a.m. |
Created at: April 8, 2026, 9:30 p.m.