Triple
T15538684
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | bull mosaic of Turin |
E370415
|
entity |
| Predicate | maintenanceNeed |
P37638
|
FINISHED |
| Object | periodic restoration |
—
|
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: periodic restoration | Statement: [bull mosaic of Turin, maintenanceNeed, periodic restoration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintenanceNeed Context triple: [bull mosaic of Turin, maintenanceNeed, periodic restoration]
-
A.
maintenanceType
Indicates the specific category or kind of maintenance activity associated with an entity or relationship.
-
B.
maintenanceNote
Indicates that there is a note or comment documenting information, instructions, or observations related to the maintenance of an entity.
-
C.
maintenance
Indicates that an entity performs, requires, or is involved in upkeep, repair, or preservation activities for another entity or system.
-
D.
maintenanceRequirement
chosen
Indicates that an entity is obligated to perform, schedule, or adhere to specific maintenance activities or conditions for another entity or system.
-
E.
maintenancePractice
Indicates the specific actions or methods used to preserve, repair, or optimize the condition or performance of something over time.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e0442f3c688190a599165e526af2ed |
completed | April 16, 2026, 2:06 a.m. |
| PD | Predicate disambiguation | batch_69deda7a95c48190bbe29fadcf17191a |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:07 a.m.