Triple
T35084890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Lyon |
E1012548
|
entity |
| Predicate | otherBeneficiary |
P182507
|
FINISHED |
| Object | Duchy of Savoy |
—
|
NE NERFINISHED |
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: Duchy of Savoy | Statement: [Treaty of Lyon, otherBeneficiary, Duchy of Savoy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: otherBeneficiary Context triple: [Treaty of Lyon, otherBeneficiary, Duchy of Savoy]
-
A.
beneficiaryBody
Indicates that one entity serves as the benefiting body or organization that receives advantage, support, or services from another entity or action.
-
B.
beneficiaryProvision
Indicates that one entity provides something (such as goods, services, or benefits) for the advantage or benefit of another entity.
-
C.
beneficiaryType
Indicates the type or category of beneficiary that receives or is intended to receive the benefit or outcome of an action or resource.
-
D.
canHaveBeneficiary
Indicates that an entity is capable of having another party designated as its beneficiary, who may receive benefits, rights, or proceeds associated with it.
-
E.
beneficiaryInstitution
Indicates that an institution is the recipient or beneficiary of an action, service, or resource.
- 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_69f76dd32c008190853aef6028f60208 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78dbf72648190a4971a558e9d1889 |
completed | May 3, 2026, 6:02 p.m. |
| PD | Predicate disambiguation | batch_69f78b8f4cc08190b49fccd798cb25d7 |
completed | May 3, 2026, 5:53 p.m. |
| PDg | Predicate description generation | batch_69f78ce43094819093857fc99f269afe |
completed | May 3, 2026, 5:59 p.m. |
Created at: May 3, 2026, 4:01 p.m.