Triple
T30126180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Lewis Christmas advert |
E765698
|
entity |
| Predicate | typicalReleaseTime |
P6833
|
FINISHED |
| Object | November |
—
|
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: November | Statement: [John Lewis Christmas advert, typicalReleaseTime, November]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalReleaseTime Context triple: [John Lewis Christmas advert, typicalReleaseTime, November]
-
A.
typicalReleaseWindow
Indicates the usual or expected time period during which something is released or made available.
-
B.
typicalReleaseScale
Indicates the usual magnitude or size of releases associated with an entity or process.
-
C.
intendedForReleaseIn
Indicates that something is planned or scheduled to be made available or launched within a specified context, such as a time, market, or platform.
-
D.
typicalAnnouncementTime
Indicates the usual or standard time at which an announcement is made or expected to occur.
-
E.
typicalTimes
chosen
Indicates the usual or characteristic times at which an event, activity, or condition typically occurs.
- 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_69f2247716748190ae4f16998f49ddf1 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a0379a4086c8190a83df5570f737e15 |
completed | May 12, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_6a037049db848190a6268bf1a8a60223 |
completed | May 12, 2026, 6:24 p.m. |
Created at: April 29, 2026, 7:14 p.m.