Triple
T15507952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Davison |
E379129
|
entity |
| Predicate | startTimeOfDoctorRole |
P34618
|
FINISHED |
| Object | 1981 |
—
|
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: 1981 | Statement: [Peter Davison, startTimeOfDoctorRole, 1981]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeOfDoctorRole Context triple: [Peter Davison, startTimeOfDoctorRole, 1981]
-
A.
hasDoctorActor
Indicates that a doctor participates as an acting agent in the specified event or relationship.
-
B.
firstAppearedWithDoctor
Indicates the specific Doctor character with whom an entity (such as a companion, monster, or concept) made its first appearance.
-
C.
startTimeOfNotableRole
chosen
Indicates the point in time when an entity began a notable role, position, or function.
-
D.
secondDoctorActor
Indicates that one entity is the actor who portrayed the second incarnation of the Doctor in the Doctor Who series in relation to another entity.
-
E.
startTimeAsAssistantAttorneyGeneral
Indicates the point in time when an individual began serving in the role of Assistant Attorney General.
- 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_69d85cd53a7c819080f5b9042c4c199e |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03fcea8888190a7b69aca360183c3 |
completed | April 16, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69ded2896a9c8190a8b9627deb3c17b4 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:55 a.m.