Triple
T32893296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Methlick |
E841396
|
entity |
| Predicate | hasNotableNearbyEstate |
P28403
|
FINISHED |
| Object | Haddo House |
—
|
NE NERFINISHED |
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: Haddo House | Statement: [Methlick, hasNotableNearbyEstate, Haddo House]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableNearbyEstate Context triple: [Methlick, hasNotableNearbyEstate, Haddo House]
-
A.
hasNeighbouringEstate
Indicates that one estate is directly adjacent to or shares a boundary with another estate.
-
B.
hasNearbyHistoricalEstate
chosen
Indicates that one entity is located close to another entity that is a recognized historical estate.
-
C.
nearbyEstate
Indicates that one estate is located close to another estate in physical space.
-
D.
hasNearbyDevelopment
Indicates that a development or construction project exists in close physical proximity to the referenced entity.
-
E.
servedNearbyEstates
Indicates that an entity provided services or assistance to estates located in its immediate geographic vicinity.
- 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_69f34945ae408190b72d8118c83beb77 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a0164b052608190adc93240dad50a06 |
completed | May 11, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_6a01637fd3ac8190970eb09650d1e659 |
completed | May 11, 2026, 5:05 a.m. |
Created at: May 1, 2026, 1:18 a.m.