Triple
T28874712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lekiu-class frigate |
E732233
|
entity |
| Predicate | helicopterTypeSupported |
P34747
|
FINISHED |
| Object | Super Lynx |
—
|
NE NERFINISHED |
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: Super Lynx | Statement: [Lekiu-class frigate, helicopterTypeSupported, Super Lynx]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helicopterTypeSupported Context triple: [Lekiu-class frigate, helicopterTypeSupported, Super Lynx]
-
A.
canOperateHelicopterType
chosen
Indicates that one entity has the ability, qualification, or authorization to operate or pilot a specified type of helicopter.
-
B.
isHelicopterOf
Indicates that one entity is a helicopter that belongs to, is operated by, or is otherwise associated with another entity.
-
C.
isHelicopterVariantOf
Indicates that one helicopter model is a modified or derived version of another helicopter model.
-
D.
isHelicopterOnly
Indicates that the subject is restricted to or designated exclusively for use by helicopters.
-
E.
helicopterService
Indicates that one entity provides or operates a helicopter-based transportation or support service for another entity or location.
- 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_69f05b06807c81909b4bbd4c20403a2b |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65a4a48888190b3c1bc721712ae71 |
completed | May 2, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 7:36 a.m.