Triple
T36565052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soyuz 4 |
E901953
|
entity |
| Predicate | transferredCrewFrom |
P155345
|
FINISHED |
| Object | Soyuz 5 |
—
|
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: Soyuz 5 | Statement: [Soyuz 4, transferredCrewFrom, Soyuz 5]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transferredCrewFrom Context triple: [Soyuz 4, transferredCrewFrom, Soyuz 5]
-
A.
carriedCrewFrom
chosen
Indicates a relationship where a vehicle or vessel transported a crew from one location or origin point to another.
-
B.
transferredPersonnelTo
Indicates that one entity moved or reassigned personnel from itself to another entity.
-
C.
crewTransferResult
Indicates the outcome or status of a process in which crew members are transferred from one assignment, location, or vehicle to another.
-
D.
plannedCrewTransferMethod
Indicates the method or means by which a crew transfer is intended or scheduled to be carried out.
-
E.
transferredSeatsTo
Indicates that one entity moved or reassigned seats it controlled or possessed to 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_69f76e6416708190a9754b8c52d4e453 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff965f9be48190b015b788207be676 |
completed | May 9, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69ff95d3015c8190b9d293fe31b859c3 |
completed | May 9, 2026, 8:15 p.m. |
Created at: May 3, 2026, 4:11 p.m.