Triple
T10787865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LEM |
E254493
|
entity |
| Predicate | roleOnApollo13 |
P95480
|
FINISHED |
| Object | emergency life-support and propulsion system |
—
|
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: emergency life-support and propulsion system | Statement: [LEM, roleOnApollo13, emergency life-support and propulsion system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleOnApollo13 Context triple: [LEM, roleOnApollo13, emergency life-support and propulsion system]
-
A.
Apollo1Crewmate
Indicates that one entity is a member of the crew of the Apollo 1 space mission in relation to another entity.
-
B.
missionRoleApollo10
Indicates that an entity held a specific mission role during the Apollo 10 spaceflight.
-
C.
crewMemberRole_JohnGlenn
Indicates that John Glenn holds or held a specific role or position as a member of a crew.
-
D.
lunarModulePilot
Indicates that the subject serves as the pilot of a lunar module in a space mission.
-
E.
crewRoleOf Wally Schirra
Indicates the specific crew position or function that Wally Schirra held within a particular mission or spacecraft crew.
- F. None of above. chosen
Provenance (4 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732d65fcc8190ab5573a861409c56 |
completed | April 9, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69d6f316940c819092a96c429629fdef |
completed | April 9, 2026, 12:30 a.m. |
| PDg | Predicate description generation | batch_69d6fa334b8c819082eaf8537084c323 |
completed | April 9, 2026, 1 a.m. |
Created at: April 8, 2026, 9:17 p.m.