Triple
T23984255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cellini Salt Cellar |
E604586
|
entity |
| Predicate | recoveredOn |
P106349
|
FINISHED |
| Object | 2006 |
—
|
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: 2006 | Statement: [Cellini Salt Cellar, recoveredOn, 2006]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recoveredOn Context triple: [Cellini Salt Cellar, recoveredOn, 2006]
-
A.
recoveryDate
chosen
Indicates the date on which a recovery process or restoration of a prior state is completed or officially recorded.
-
B.
recoveredIn
Indicates that something lost, damaged, or impaired has been restored or regained within a particular context, process, or location.
-
C.
recoveredFrom
Indicates that an entity has returned to a normal or improved state after previously experiencing or being affected by another specified condition, event, or problem.
-
D.
recovered
Indicates that an entity has returned to a previous, healthier, normal, or functional state after a period of loss, damage, illness, or impairment.
-
E.
recoveredThrough
Indicates that something was regained, restored, or obtained again by means of a specified method, process, or intermediary.
- 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_69e29543f40c819087700b7a272afb60 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d2c045e081909b70d9aabbe4fdd2 |
completed | April 29, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:31 p.m.