Triple
T17046527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donna Noble |
E413583
|
entity |
| Predicate | memoryOfDoctor |
P89852
|
FINISHED |
| Object | erased to save her life |
—
|
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: erased to save her life | Statement: [Donna Noble, memoryOfDoctor, erased to save her life]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memoryOfDoctor Context triple: [Donna Noble, memoryOfDoctor, erased to save her life]
-
A.
doctorNumber
Indicates the unique identifying number assigned to a doctor in the context of a relationship or record.
-
B.
hasDoctorActor
Indicates that a doctor participates as an acting agent in the specified event or relationship.
-
C.
builtInMemoryOf
Indicates that something was constructed as a tribute or commemoration to a particular person, group, or event.
-
D.
featuredDoctor
Indicates that a particular doctor is highlighted or promoted as a primary or notable medical professional in a given context.
-
E.
память
chosen
Indicates a relationship where an entity retains, recalls, or is associated with stored information, experiences, or data.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3da9e3d8881909f197aba0e4c97e7 |
completed | April 18, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.