Triple
T27471366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adelaide Brooke |
E693327
|
entity |
| Predicate | appearsWithDoctor |
P162421
|
FINISHED |
| Object | Tenth Doctor |
—
|
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: Tenth Doctor | Statement: [Adelaide Brooke, appearsWithDoctor, Tenth Doctor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appearsWithDoctor Context triple: [Adelaide Brooke, appearsWithDoctor, Tenth Doctor]
-
A.
encountersDoctor
chosen
Indicates that one entity comes into contact with or meets a doctor in some context or situation.
-
B.
firstAppearedWithDoctor
Indicates the specific Doctor character with whom an entity (such as a companion, monster, or concept) made its first appearance.
-
C.
hasDoctorActor
Indicates that a doctor participates as an acting agent in the specified event or relationship.
-
D.
featuredDoctor
Indicates that a particular doctor is highlighted or promoted as a primary or notable medical professional in a given context.
-
E.
hasSeriesDoctor
Indicates that a particular doctor is associated with or responsible for a given series (such as a TV show, book series, or medical series).
- 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_69ef538105548190a771cc5a0cf8c211 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 27, 2026, 12:54 p.m.