Triple
T29842410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dying Swan |
E757836
|
entity |
| Predicate | signatureRoleOf |
P170438
|
FINISHED |
| Object | Anna Pavlova |
—
|
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: Anna Pavlova | Statement: [The Dying Swan, signatureRoleOf, Anna Pavlova]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signatureRoleOf Context triple: [The Dying Swan, signatureRoleOf, Anna Pavlova]
-
A.
signatureRole
Indicates the specific function or capacity in which an entity participates in a signing or signature-related action.
-
B.
signatureEventOf
Indicates that a given event represents or records the signing (or creation) of the associated entity, such as a document, agreement, or artifact.
-
C.
signatureConcept
Indicates that one concept is the defining or characteristic idea that most distinctly represents or identifies another concept.
-
D.
signatoryAuthority
Indicates that an entity has the legal power or authorization to sign documents or agreements on behalf of another party.
-
E.
signatureSubject
Indicates that an entity serves as the subject or principal party associated with a given signature.
- 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_69f224593f6c81908785a560fe659f58 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
| PDg | Predicate description generation | batch_69f68f6584a88190a8c4d95c0c84bee9 |
completed | May 2, 2026, 11:57 p.m. |
Created at: April 29, 2026, 5:40 p.m.