Triple
T1393271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Coast Guard cutters |
E30608
|
entity |
| Predicate | hasMinimumLength |
P27681
|
FINISHED |
| Object | 65 feet |
—
|
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: 65 feet | Statement: [U.S. Coast Guard cutters, hasMinimumLength, 65 feet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMinimumLength Context triple: [U.S. Coast Guard cutters, hasMinimumLength, 65 feet]
-
A.
hasMinimumValue
Indicates that an entity possesses a value that is the lowest permissible or observed within a specified set, range, or context.
-
B.
isMinimumWhen
Indicates that a value or state is at its smallest or least level precisely under certain specified conditions or circumstances.
-
C.
meetsAtLeast
Indicates that one entity encounters or comes into contact with another entity at least a specified minimum number of times or to a minimum required degree.
-
D.
hasMaximumValue
Indicates that one value in a set is the greatest or highest possible according to a specified criterion.
-
E.
minimumWidth
Indicates that there is a specified smallest allowable or required width for something in the relationship.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c37cd99081908d16014e0b99992d |
completed | March 1, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4c13270d8819081d8ee1be34cabf5 |
completed | March 1, 2026, 10:44 p.m. |
Created at: March 1, 2026, 7:59 p.m.