Triple
T22692383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cajal bodies |
E561083
|
entity |
| Predicate | disassemblesDuring |
P77993
|
FINISHED |
| Object | mitosis |
—
|
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: mitosis | Statement: [Cajal bodies, disassemblesDuring, mitosis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disassemblesDuring Context triple: [Cajal bodies, disassemblesDuring, mitosis]
-
A.
disassembledAfter
Indicates that one entity was taken apart or broken down into its components at a point in time later than another specified event or state.
-
B.
dismantledBy
Indicates that something has been taken apart, disassembled, or broken down by a particular agent or entity.
-
C.
dismantledIn
chosen
Indicates that an entity was taken apart, disassembled, or broken down within a specified context, such as a particular time, place, or event.
-
D.
deconstructs
Indicates that one entity systematically takes apart, analyzes, or dismantles another entity or its structure into constituent elements.
-
E.
canBeDissectedBy
Indicates that one entity is capable of being divided or analyzed into parts by another entity or method.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789ba0148190891781d05ec64f3c |
completed | April 29, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69ee62b2259c819091ed1387a748b9f3 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:13 p.m.