Triple
T35832156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas P. Stafford |
E1035827
|
entity |
| Predicate | roleInApolloSoyuzTestProject |
P48933
|
FINISHED |
| Object | American commander |
—
|
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: American commander | Statement: [Thomas P. Stafford, roleInApolloSoyuzTestProject, American commander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInApolloSoyuzTestProject Context triple: [Thomas P. Stafford, roleInApolloSoyuzTestProject, American commander]
-
A.
missionRoleApolloSoyuz
chosen
Indicates that an entity held a specific role or function in the Apollo–Soyuz space mission.
-
B.
spaceShuttleRole
Indicates the specific function or duty an entity has in relation to a space shuttle (e.g., its operational, crew, or mission role).
-
C.
crewRole_SergeiKrikalev
Indicates that there is a specified crew role or position associated with Sergei Krikalev within a particular mission or crew context.
-
D.
operatorOfSpaceMission
Indicates that one entity is the organization or individual responsible for operating or managing a specific space mission.
-
E.
missionCrewRole
Indicates the specific role or function an individual holds as a member of a mission’s crew.
- 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_69f76e192a94819082db360cb91e6a8d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a0160834e388190908591b300954d29 |
completed | May 11, 2026, 4:52 a.m. |
| PD | Predicate disambiguation | batch_6a01602a83408190a11d754bdc7da0e9 |
completed | May 11, 2026, 4:50 a.m. |
Created at: May 3, 2026, 4:06 p.m.