Triple
T25783445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Borderland State Park |
E649353
|
entity |
| Predicate | AmesMansionStyle |
P156653
|
FINISHED |
| Object | stone mansion |
—
|
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: stone mansion | Statement: [Borderland State Park, AmesMansionStyle, stone mansion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AmesMansionStyle Context triple: [Borderland State Park, AmesMansionStyle, stone mansion]
-
A.
AmesMansionInstanceOf
Indicates that something is classified as an instance of the Ames Mansion.
-
B.
associatedHouseStyle
chosen
Indicates a relationship where a house or building is linked to a particular architectural style or design tradition.
-
C.
keeperHouseStyle
Indicates the architectural or design style associated with a keeper’s house (e.g., lighthouse keeper’s residence).
-
D.
countryHouseStyle
Indicates a stylistic relationship where something is designed, built, or decorated in the manner or aesthetic of a country house.
-
E.
hasTraditionalHouseStyle
Indicates that an entity possesses or is characterized by a traditional style of house or residential architecture.
- 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_69e7ab33e9308190afe415dc6f9e8876 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fe628ff88190802a8c3d39d06d42 |
completed | May 2, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69f4a0fed15881909b789251fe5d8d45 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 22, 2026, 5:52 a.m.