Triple
T2049217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government House, Wellington |
E45524
|
entity |
| Predicate | groundsFeature |
P5378
|
FINISHED |
| Object | formal gardens |
—
|
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: formal gardens | Statement: [Government House, Wellington, groundsFeature, formal gardens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: groundsFeature Context triple: [Government House, Wellington, groundsFeature, formal gardens]
-
A.
terrainFeature
chosen
Indicates a relationship where one entity is a natural or constructed landform or surface characteristic associated with a given location or area.
-
B.
ground
Indicates that one entity is in contact with or supported by the ground or a ground-like surface.
-
C.
groundComponent
Indicates that one entity serves as a foundational or base part upon which another entity is built, attached, or functionally dependent.
-
D.
featureOfInterest
Indicates the entity or object that is the primary subject or focus of the described observation, measurement, or analysis.
-
E.
featuresLocation
Indicates that something is characterized by or includes a specific location as one of its notable attributes.
- 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_69a8891948208190ab7898da21824c77 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb98c70c48190beb98aad56d9daf1 |
completed | March 7, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_69abb7abba508190b872f345d3ba51bb |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:39 p.m.