Triple
T12058921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mesembryanthemum crystallinum |
E287113
|
entity |
| Predicate | specializedCells |
P3601
|
FINISHED |
| Object | epidermal bladder cells |
—
|
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: epidermal bladder cells | Statement: [Mesembryanthemum crystallinum, specializedCells, epidermal bladder cells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specializedCells Context triple: [Mesembryanthemum crystallinum, specializedCells, epidermal bladder cells]
-
A.
cellType
chosen
Indicates the classification relationship that specifies what type of cell an entity is or is associated with.
-
B.
isSpecializedFor
Indicates that one entity is specifically adapted, designed, or focused to perform optimally for a particular function, context, or domain associated with another entity.
-
C.
specializationRegion
Indicates that something is specialized, adapted, or specifically applicable to a particular geographic or spatial region.
-
D.
oblast specializace
Indicates a relationship where an entity has a particular field or area of specialization.
-
E.
specializationOrder
Indicates that one entity is a more specific or specialized version of another within a hierarchical ordering of concepts or types.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:47 p.m.