Triple
T28611395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ScyllaDB |
E724173
|
entity |
| Predicate | dropInReplacementFor |
P114659
|
FINISHED |
| Object | Apache Cassandra |
—
|
NE NERFINISHED |
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: Apache Cassandra | Statement: [ScyllaDB, dropInReplacementFor, Apache Cassandra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dropInReplacementFor Context triple: [ScyllaDB, dropInReplacementFor, Apache Cassandra]
-
A.
replacedWith
Indicates that one entity has been substituted or superseded by another entity, taking over its role, function, or position.
-
B.
placedBy
Indicates that one entity was positioned, set, or put in a location or context by another entity.
-
C.
seeksToReplace
Indicates an intention or effort by one entity to take over the role, function, or position currently held by another entity.
-
D.
developedAsReplacementFor
chosen
Indicates that one entity was created or designed specifically to take the place of another entity, serving as its successor or substitute.
-
E.
replacementProject
Indicates that one entity is a project intended to replace or supersede another entity or project.
- 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:30 a.m.