Triple
T29577813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conshelf II habitat |
E753491
|
entity |
| Predicate | crewDesignation |
P21064
|
FINISHED |
| Object | aquanauts |
—
|
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: aquanauts | Statement: [Conshelf II habitat, crewDesignation, aquanauts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewDesignation Context triple: [Conshelf II habitat, crewDesignation, aquanauts]
-
A.
crewVariantName
Indicates the specific name or label assigned to a particular variant or version of a crew configuration.
-
B.
bulletDesignation
Indicates that one entity is designated or labeled as a specific bullet point or bullet-style marker in relation to another entity.
-
C.
crewType
chosen
Indicates the specific role or category of crew associated with an entity, such as the type of personnel assigned to operate or support it.
-
D.
sideDesignation
Indicates how an entity is classified or labeled with respect to a particular side, position, or alignment within a relationship or context.
-
E.
systemDesignation
Indicates that an entity has been assigned a specific formal label or identifier within a defined system or framework.
- 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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66d7765208190b87b1cc6d96a151c |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:04 p.m.