Triple
T28030260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soyuz TM-13 |
E708244
|
entity |
| Predicate | relatedLongDurationCrewMember |
P42937
|
FINISHED |
| Object | Sergei Krikalev |
—
|
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: Sergei Krikalev | Statement: [Soyuz TM-13, relatedLongDurationCrewMember, Sergei Krikalev]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedLongDurationCrewMember Context triple: [Soyuz TM-13, relatedLongDurationCrewMember, Sergei Krikalev]
-
A.
relatedCastMember
Indicates that two cast members are connected through a relevant relationship, such as working together on the same production or being otherwise professionally associated.
-
B.
hasCrewMember
chosen
Indicates that an entity includes or employs another entity as a member of its crew.
-
C.
hasRelativeInCastOrCrew
Indicates that at least one member of a work’s cast or crew is a relative of a specified person.
-
D.
hasCrewRole
Indicates that an entity serves in a specific role or position within a crew associated with another entity.
-
E.
laterCastMember
Indicates that one entity joined the cast of a show, film, or production at a later time than another cast member.
- 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_69ef9b6bdd9c8190bb3a574a03774ad1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69ffb69812808190a751853b30183e65 |
completed | May 9, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69ffb63bdda88190a9dd8426dc0bad43 |
completed | May 9, 2026, 10:33 p.m. |
Created at: April 27, 2026, 8:15 p.m.