Triple
T35020764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Christmas Invasion |
E1010188
|
entity |
| Predicate | introducesIncarnationOfTheDoctor |
P122978
|
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: [The Christmas Invasion, introducesIncarnationOfTheDoctor, Tenth Doctor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducesIncarnationOfTheDoctor Context triple: [The Christmas Invasion, introducesIncarnationOfTheDoctor, Tenth Doctor]
-
A.
featuresIncarnationOfDoctor
Indicates that the subject includes or presents a specific incarnation (version) of the Doctor character.
-
B.
introducesIncarnation
chosen
Indicates that one entity brings about, initiates, or presents the embodiment or incarnation of another entity in a concrete or manifest form.
-
C.
firstAppearanceAsTheDoctor
Indicates the event or work in which an actor portrays the Doctor character for the first time.
-
D.
associatedDoctorIncarnation
Indicates a relationship where a particular doctor is linked to a specific incarnation or version of that doctor.
-
E.
hasDoctorIncarnation
Indicates that an entity is associated with a specific incarnation or version of the Doctor (e.g., a particular regeneration or portrayal).
- 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_69f76dcc3ac8819096a3ed52f5fa2523 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe163a41a0819098403b470e327d29 |
completed | May 8, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fe1358db5c819092570814a37ef5bd |
completed | May 8, 2026, 4:46 p.m. |
Created at: May 3, 2026, 4:01 p.m.