Triple
T30167062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thirlwall Castle |
E766823
|
entity |
| Predicate | stateOfUse |
P65653
|
FINISHED |
| Object | abandoned as a residence |
—
|
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: abandoned as a residence | Statement: [Thirlwall Castle, stateOfUse, abandoned as a residence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateOfUse Context triple: [Thirlwall Castle, stateOfUse, abandoned as a residence]
-
A.
usedInState
Indicates that something is employed, applied, or functions within a particular state or condition.
-
B.
usageStatus
chosen
Indicates the current state or condition of how something is being used, such as whether it is active, inactive, available, or in use.
-
C.
usedByStateOrTerritory
Indicates that something (such as an object, system, or resource) is utilized or employed by a specific state or territory.
-
D.
designationUsedFor
Indicates that a particular name, label, or title is employed to refer to or identify a specific entity or role.
-
E.
stateCurrently
Indicates that something is in a particular state or condition at the present moment.
- 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_69f2247a968881909d79c18f2bfcb275 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd0d0ba5c48190bddb3f0e6637544c |
completed | May 7, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69fd0c4324a8819086c90adf46216e0e |
completed | May 7, 2026, 10:03 p.m. |
Created at: April 29, 2026, 7:23 p.m.