Triple
T9721323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luts’k |
E235479
|
entity |
| Predicate | hasWellPreserved |
P9592
|
FINISHED |
| Object | medieval castle |
—
|
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: medieval castle | Statement: [Luts’k, hasWellPreserved, medieval castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWellPreserved Context triple: [Luts’k, hasWellPreserved, medieval castle]
-
A.
hasSubjectOfPreservation
Indicates that something is the specific focus or object being preserved or conserved within a preservation relationship.
-
B.
hasPreservationConditions
Indicates the specific environmental or handling conditions required to properly preserve or maintain an entity.
-
C.
somePreservedAs
Indicates that at least one part or instance of an entity is kept or maintained in a particular state, form, or condition.
-
D.
stateOfPreservation
chosen
Indicates the condition or degree to which something has been maintained, conserved, or kept intact over time.
-
E.
hasPreservationActivity
Indicates that an entity is involved in, or associated with, a specific preservation-related action or process.
- 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_69ca84d0123c819096f9dc3b6abb0881 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e42ce948190b52791b27c4456dc |
completed | April 1, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69cd03bfeca08190924fca43aaa9c10f |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:20 p.m.