Triple
T3202660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cavernas cemetery |
E67085
|
entity |
| Predicate | hasPreservationConditions |
P46120
|
FINISHED |
| Object | arid environment |
—
|
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: arid environment | Statement: [Cavernas cemetery, hasPreservationConditions, arid environment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreservationConditions Context triple: [Cavernas cemetery, hasPreservationConditions, arid environment]
-
A.
stateOfPreservation
Indicates the condition or degree to which something has been maintained, conserved, or kept intact over time.
-
B.
preservationType
Indicates the method or process by which something is preserved or kept from deterioration.
-
C.
preservationMethod
Indicates the technique or process used to maintain, protect, or prolong the condition, quality, or usability of something over time.
-
D.
preservedAt
Indicates that something is kept, maintained, or conserved in a particular place or context.
-
E.
typeOfPreservationLaw
Indicates the specific category or kind of preservation law that governs how something is protected or conserved.
- 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_69ad8589bd988190afa7ed2bdffb7b33 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada9b188a88190b7b5e9b3be9410db |
completed | March 8, 2026, 4:54 p.m. |
| PD | Predicate disambiguation | batch_69ad9e078f7c8190813d9fcb4f5071fb |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada0f9259c8190afbc5ad0fa55436b |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:07 p.m.