Triple
T11036791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jonathan Creek |
E260905
|
entity |
| Predicate | laterSpecialsAired |
P16447
|
FINISHED |
| Object | after 2004 |
—
|
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: after 2004 | Statement: [Jonathan Creek, laterSpecialsAired, after 2004]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterSpecialsAired Context triple: [Jonathan Creek, laterSpecialsAired, after 2004]
-
A.
specialEpisodeAirDate
Indicates the calendar date on which a special episode is broadcast or made available to the public.
-
B.
specialBroadcasts
Indicates that one entity transmits or airs a broadcast that is designated as special or exceptional in some way to another entity or audience.
-
C.
hasTVSpecial
Indicates that an entity has an associated television special featuring it as the main subject or focus.
-
D.
hasStandUpSpecial
Indicates that an entity has created, performed, or released a stand-up comedy special.
-
E.
includesSpecialEpisodes
chosen
Indicates that the subject collection or series contains one or more special, non-regular episodes.
- 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_69d6aa979bdc8190bf0e79104cc098c1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d797e9e3fc8190802195ac9fcb8e28 |
completed | April 9, 2026, 12:13 p.m. |
| PD | Predicate disambiguation | batch_69d74407cb088190ba37c8da3d342b64 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:25 p.m.