Triple
T6252714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arundel |
E140085
|
entity |
| Predicate | castleCurrentUse |
P69727
|
FINISHED |
| Object | seat of the Duke of Norfolk |
—
|
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: seat of the Duke of Norfolk | Statement: [Arundel, castleCurrentUse, seat of the Duke of Norfolk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: castleCurrentUse Context triple: [Arundel, castleCurrentUse, seat of the Duke of Norfolk]
-
A.
castleBuilt
Indicates that a castle has been constructed or established, typically by a specific agent or during a particular time period.
-
B.
castleBuiltFor
Indicates that a castle was constructed specifically for the benefit, use, or commission of a particular person, group, or purpose.
-
C.
castleName
Indicates that an entity has the specified name of a castle.
-
D.
castleLaterOwnedBy
Indicates that ownership of a castle passed to a specified entity at a later time than the initial or previously recorded owner.
-
E.
castleOverlooks
Indicates that a castle is positioned so that it has a clear, elevated view over a particular area, object, or landscape.
- 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_69c008b4858c819095b0199114a9a87b |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063417c8c8190945049881819d307 |
completed | March 22, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69c05605566c81908e197f5accd072d2 |
completed | March 22, 2026, 8:50 p.m. |
| PDg | Predicate description generation | batch_69c05707d5408190a1d0fd80414ad957 |
completed | March 22, 2026, 8:54 p.m. |
Created at: March 22, 2026, 4:24 p.m.