Triple
T7685762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theodor Svedberg |
E174110
|
entity |
| Predicate | notableInstrumentDeveloped |
P71418
|
FINISHED |
| Object | ultracentrifuge |
—
|
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: ultracentrifuge | Statement: [Theodor Svedberg, notableInstrumentDeveloped, ultracentrifuge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableInstrumentDeveloped Context triple: [Theodor Svedberg, notableInstrumentDeveloped, ultracentrifuge]
-
A.
notableInstrumentBuilt
chosen
Indicates that an entity is notable for having built or constructed a particular instrument.
-
B.
notableInstrument
Indicates that an entity is especially known for playing or being associated with a particular musical instrument.
-
C.
notableInstrumentTechnique
Indicates that an entity is particularly recognized for using, developing, or being associated with a specific musical instrument technique.
-
D.
introducedInstrument
Indicates that one entity caused or brought about the initial use or adoption of a particular instrument by another entity or within a given context.
-
E.
discoveredWithInstrument
Indicates that something was discovered through the use of a specified instrument or tool.
- 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_69c6995840408190a19de6c51090f46f |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c706d1f0208190bc5b695aa5736244 |
completed | March 27, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69c70163dea88190ae729df50e63dfd7 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:02 p.m.