Triple
T31416087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic Star |
E801396
|
entity |
| Predicate | minimumQualifyingService |
P174955
|
FINISHED |
| Object | six months at sea |
—
|
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: six months at sea | Statement: [Atlantic Star, minimumQualifyingService, six months at sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumQualifyingService Context triple: [Atlantic Star, minimumQualifyingService, six months at sea]
-
A.
qualifyingService
Indicates that an entity provides a service that meets specified criteria or standards required for a particular purpose or status.
-
B.
minimumServiceFor18YearClass
Indicates that there is a required minimum length or level of service associated with an 18-year service class or category.
-
C.
minimumServiceFor25YearClass
Indicates the minimum level or amount of service required for entities that fall into the 25-year service class.
-
D.
minimumGrant
Indicates that there is a lowest allowable or required amount of a grant associated with an entity or agreement.
-
E.
providedQualificationFor
Indicates that one entity supplied or granted a qualification, credential, or certification that another entity possesses or uses.
- 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_69f348c0dd648190bf2fd7642f78eb06 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6cd9bae8c8190b528641499162a75 |
completed | May 3, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
| PDg | Predicate description generation | batch_69f6cd119cac8190a0b3ebe8b9c742c2 |
completed | May 3, 2026, 4:20 a.m. |
Created at: April 30, 2026, 8:43 p.m.