Triple
T25926494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMAS Canberra (L02) |
E653318
|
entity |
| Predicate | landingCraftCarried |
P2774
|
FINISHED |
| Object |
LHD Landing Craft (LLC)
The LHD Landing Craft (LLC) is a class of Australian Navy amphibious vessels designed to transport troops, vehicles, and equipment between amphibious assault ships and shore.
|
E1701376
|
NE FINISHED |
How this triple was built (3 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: LHD Landing Craft (LLC) | Statement: [HMAS Canberra (L02), landingCraftCarried, LHD Landing Craft (LLC)]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: LHD Landing Craft (LLC) Triple: [HMAS Canberra (L02), landingCraftCarried, LHD Landing Craft (LLC)]
Generated description
The LHD Landing Craft (LLC) is a class of Australian Navy amphibious vessels designed to transport troops, vehicles, and equipment between amphibious assault ships and shore.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: landingCraftCarried Context triple: [HMAS Canberra (L02), landingCraftCarried, LHD Landing Craft (LLC)]
-
A.
landingCraft
Indicates a vehicle or vessel specifically used to transport and set down people or cargo from one location onto a surface, typically from water or air to land.
-
B.
carriedBy
chosen
Indicates that one entity is physically supported and transported by another entity.
-
C.
hasAmphibiousCapability
Indicates that an entity possesses the ability to operate effectively in both water and land environments.
-
D.
amphibiousCapacity
Indicates the ability of an entity to operate effectively in both water and on land.
-
E.
designedToEmbark
Indicates that something is created or configured with the specific purpose of beginning or initiating a journey, process, or undertaking.
- F. None of above.
Provenance (6 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_69e7ab3eb9b881909c1390690551f868 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6041473b08190a9b421b06f24b615 |
completed | May 2, 2026, 2:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a10ecd5d7608190ba6aeaac8d3e8531 |
completed | May 22, 2026, 11:55 p.m. |
| NEDg | Description generation | batch_6a10ef77bd948190a61d380e7a5b3f62 |
completed | May 23, 2026, 12:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a10eff47f048190bb3bd46ff186889c |
completed | May 23, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69f4a10480748190a2e67bd399fc435d |
completed | May 1, 2026, 12:48 p.m. |
Created at: April 22, 2026, 8:35 a.m.