Triple
T15704288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jam |
E380667
|
entity |
| Predicate | isCommonlySpreadOn |
P33560
|
FINISHED |
| Object | bread |
—
|
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: bread | Statement: [Jam, isCommonlySpreadOn, bread]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCommonlySpreadOn Context triple: [Jam, isCommonlySpreadOn, bread]
-
A.
transmissionBetweenHumans
Indicates that something (such as a disease, information, or influence) is passed directly from one human to another.
-
B.
commonlyFoundOn
chosen
Indicates that one entity is typically or frequently located on, attached to, or present upon another entity.
-
C.
modeOfTransmission
Indicates the method or pathway through which something, typically a disease or information, is passed from one source to another.
-
D.
spreadingStatus
Indicates the current state or progression of how something is spreading or being disseminated (e.g., whether and how it is expanding, stable, or declining).
-
E.
commonlyIdentifiedWith
Indicates that two entities are widely regarded or treated as the same or equivalent, even if they are formally distinct.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b4d6b5788190883746ee82c799f5 |
completed | April 16, 2026, 10:07 a.m. |
| PD | Predicate disambiguation | batch_69e0051d639481909a10614e8f83e659 |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:45 a.m.