Triple
T29108173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KEGG pathways |
E736820
|
entity |
| Predicate | hasRepresentationFormat |
P107278
|
FINISHED |
| Object | KEGG pathway maps |
—
|
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: KEGG pathway maps | Statement: [KEGG pathways, hasRepresentationFormat, KEGG pathway maps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRepresentationFormat Context triple: [KEGG pathways, hasRepresentationFormat, KEGG pathway maps]
-
A.
representsInFormat
Indicates that one entity is expressed, encoded, or presented using the specific format defined by another entity.
-
B.
hasFormatSpecification
chosen
Indicates that something is associated with a particular format definition or specification that describes how it should be structured or represented.
-
C.
hasShowFormat
Indicates that something (such as a show or program) is associated with or presented in a particular format or style.
-
D.
hasSecondaryFormat
Indicates that an entity is associated with an additional, alternative, or supplementary format beyond its primary format.
-
E.
presentedInFormat
Indicates that something is expressed, delivered, or made available using a particular format or representation.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ffb97b8ff8819088b105d99a0820c9 |
completed | May 9, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69ffb88ef7388190a710120ed76edc0e |
completed | May 9, 2026, 10:43 p.m. |
Created at: April 28, 2026, 11:16 a.m.