Triple
T22357084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calvin cycle |
E552680
|
entity |
| Predicate | regenerates |
P121846
|
FINISHED |
| Object | ribulose-1,5-bisphosphate |
—
|
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: ribulose-1,5-bisphosphate | Statement: [Calvin cycle, regenerates, ribulose-1,5-bisphosphate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regenerates Context triple: [Calvin cycle, regenerates, ribulose-1,5-bisphosphate]
-
A.
regenerationOf
Indicates that one entity is the renewed, restored, or regrown version of another entity, typically after damage, loss, or degradation.
-
B.
regeneratedWhen
Indicates that an entity is brought back, restored, or recreated at a specific time or under specific conditions.
-
C.
regeneratesIn
Indicates that an entity restores or regrows itself within, or as a result of conditions in, a specified environment, context, or time period.
-
D.
regenerationRetcon
Indicates a continuity-altering change where a character’s regeneration or renewal is retroactively modified, redefined, or overwritten in the narrative.
-
E.
regenerationSource
chosen
Indicates that one entity serves as the origin, cause, or provider for the restoration or regrowth of another entity.
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157d08b148190a9a4e445e8579219 |
completed | April 29, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69e7300c20088190a59e5bf9e70384f3 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:44 p.m.