Triple
T23378766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Star (London newspaper) |
E593679
|
entity |
| Predicate | primaryDistributionTime |
P18068
|
FINISHED |
| Object | evening |
—
|
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: evening | Statement: [The Star (London newspaper), primaryDistributionTime, evening]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryDistributionTime Context triple: [The Star (London newspaper), primaryDistributionTime, evening]
-
A.
primaryDistribution
Indicates that one entity serves as the main or principal channel through which another entity is distributed or allocated.
-
B.
laterDistributedOn
Indicates that something was distributed or made available at a time later than a referenced distribution or event date.
-
C.
supportsTimeDistribution
Indicates that one entity provides or enables the allocation, scheduling, or distribution of time-related resources or events for another entity.
-
D.
intendedDistribution
Indicates the planned or expected way in which something is to be distributed among recipients or locations.
-
E.
peakDeliveryTime
chosen
Indicates the time period during which deliveries are expected to be at their highest volume or frequency.
- 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_69e25d268a50819095f2fd479da8ef3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3b5e4f0819081a5d4586796677b |
completed | April 29, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69f061c7aaa48190a58ce93f87155ffc |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:33 p.m.