Triple
T3357440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drakensteyn Castle |
E70638
|
entity |
| Predicate | hasWoodland |
P6742
|
FINISHED |
| Object | surrounding forested estate |
—
|
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: surrounding forested estate | Statement: [Drakensteyn Castle, hasWoodland, surrounding forested estate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWoodland Context triple: [Drakensteyn Castle, hasWoodland, surrounding forested estate]
-
A.
locatedInForest
Indicates that an entity is situated within the boundaries of a forest.
-
B.
hasNearbyForestType
Indicates that one entity is located close to, or in the vicinity of, a forest of a specified type.
-
C.
hasTrees
chosen
Indicates that something possesses or contains one or more trees.
-
D.
hasMeadow
Indicates that one entity possesses, contains, or includes a meadow as part of its area or composition.
-
E.
hasNationalForest
Indicates that a place or jurisdiction contains, includes, or is home to at least one designated national forest.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb244435c81908e35d2aa36ec4f46 |
completed | March 8, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.