Triple
T12773717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunstan Cass |
E305313
|
entity |
| Predicate | stolenObject |
P64622
|
FINISHED |
| Object | Silas Marner’s hoard of gold |
—
|
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: Silas Marner’s hoard of gold | Statement: [Dunstan Cass, stolenObject, Silas Marner’s hoard of gold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stolenObject Context triple: [Dunstan Cass, stolenObject, Silas Marner’s hoard of gold]
-
A.
stolenBy
Indicates that something has been taken unlawfully or without permission by a particular entity.
-
B.
stolenDuring
Indicates that one entity was stolen in the course of, or at the time of, another specified event or time period.
-
C.
stolenFrom
chosen
Indicates that something was taken unlawfully from a particular source or owner.
-
D.
theftStatus
Indicates the current state or condition of an entity with respect to being stolen, such as whether it has been reported, confirmed, or suspected as theft.
-
E.
collectionBeforeTheft
Indicates that a collection or gathering of items occurred prior to the act of theft.
- 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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96df5b68481908a5d40516b09be52 |
completed | April 10, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69d96409739881909174ba005a986cb5 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:28 p.m.