Triple
T37634901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Propionibacterium |
E936461
|
entity |
| Predicate | primaryMetabolicProduct |
P7216
|
FINISHED |
| Object | propionic acid |
—
|
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: propionic acid | Statement: [Propionibacterium, primaryMetabolicProduct, propionic acid]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryMetabolicProduct Context triple: [Propionibacterium, primaryMetabolicProduct, propionic acid]
-
A.
primaryMetabolite
Indicates that one entity is a primary metabolite, i.e., a small molecule directly involved in essential cellular metabolic processes.
-
B.
hasMainMetabolite
Indicates that one substance is the primary metabolite produced from the biotransformation of another substance.
-
C.
isMetabolizedBy
Indicates that a substance is biochemically broken down or transformed through metabolic processes carried out by a specified organism, cell type, or enzyme system.
-
D.
primaryProduct
chosen
Indicates that one entity is the main or most important product associated with, produced by, or offered by another entity.
-
E.
metabolismType
Indicates the kind of metabolic process or pathway an entity uses to obtain and transform energy or nutrients.
- 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_69f76ed31d8881908405da6c6d2f0463 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.