Triple
T27662454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chubby |
E697154
|
entity |
| Predicate | cellComposition |
P4603
|
FINISHED |
| Object | small set of replicas |
—
|
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: small set of replicas | Statement: [Chubby, cellComposition, small set of replicas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cellComposition Context triple: [Chubby, cellComposition, small set of replicas]
-
A.
cellularComponent
Indicates the relationship between a biological entity and the specific cellular location or structure in which it is physically present or functions.
-
B.
cellStructure
chosen
Indicates the structural organization, components, and physical arrangement that make up a cell.
-
C.
cellularOrganization
Indicates how the components within a biological cell are structured, arranged, and functionally organized in relation to one another.
-
D.
cellBiologyFeature
Indicates a relationship where a biological entity possesses or is characterized by a specific cellular-level property, structure, or function.
-
E.
seedComposition
Indicates the relationship specifying what substances or components make up a seed.
- 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f634a183bc8190bdb59700f8f0a16e |
completed | May 2, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:37 p.m.