Triple
T4090103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | wet feet, dry feet policy |
E87684
|
entity |
| Predicate | appliesToRoute |
P1129
|
FINISHED |
| Object | sea routes between Cuba and the United States |
—
|
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: sea routes between Cuba and the United States | Statement: [wet feet, dry feet policy, appliesToRoute, sea routes between Cuba and the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToRoute Context triple: [wet feet, dry feet policy, appliesToRoute, sea routes between Cuba and the United States]
-
A.
isRouteFor
Indicates that one entity serves as a path, course, or channel used for traveling, transporting, or connecting to another entity.
-
B.
appliesTo
chosen
Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
-
C.
appliesToFeature
Indicates that something (such as a rule, constraint, or configuration) is relevant to, or governs, a specific feature.
-
D.
hasRoute
Indicates that there exists a path or connection enabling travel or communication from one entity to another.
-
E.
appliesFrom
Indicates that a rule, condition, or effect begins to be applicable starting from a specific point in time or state.
- 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_69aed94425148190be337845d56fac22 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcab0a1c8190a1b0ca48ebc95b31 |
completed | March 9, 2026, 5 p.m. |
| PD | Predicate disambiguation | batch_69aef909c9c88190b09d48dad325a83c |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:39 p.m.