Triple
T36812213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soyuz 10 |
E909624
|
entity |
| Predicate | researchEngineer |
P122756
|
FINISHED |
| Object | Nikolai Rukavishnikov |
—
|
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: Nikolai Rukavishnikov | Statement: [Soyuz 10, researchEngineer, Nikolai Rukavishnikov]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: researchEngineer Context triple: [Soyuz 10, researchEngineer, Nikolai Rukavishnikov]
-
A.
researchOperator
Indicates that an entity conducts, manages, or is responsible for carrying out research activities on or for another entity.
-
B.
researchArm
Indicates that an entity is a specific study group or treatment arm within a research or clinical trial design.
-
C.
engineeringRole
chosen
Indicates that an entity holds or is associated with a role or position in the field of engineering.
-
D.
engineeringContribution
Indicates a relationship where an entity contributes engineering work, expertise, or effort toward the design, development, or improvement of another entity.
-
E.
researchPlatform
Indicates that an entity serves as a platform or environment specifically designed to support, host, or facilitate research activities or projects for 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_69f76e7cbbf48190891227b14d041139 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.