Triple
T3274140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RV Kilo Moana |
E68718
|
entity |
| Predicate | builder |
P3143
|
FINISHED |
| Object |
Atlantic Marine
Atlantic Marine is a shipbuilding company known for constructing specialized research and commercial vessels.
|
E341207
|
NE FINISHED |
How this triple was built (4 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: Atlantic Marine | Statement: [RV Kilo Moana, builder, Atlantic Marine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atlantic Marine Context triple: [RV Kilo Moana, builder, Atlantic Marine]
-
A.
Jersey Marine
Jersey Marine is a coastal village in South Wales known for its proximity to Swansea Bay and its historic tower landmark.
-
B.
Caladan Oceanic
Caladan Oceanic is a private deep-sea exploration company known for organizing and conducting record-breaking manned expeditions to the deepest points in the world’s oceans.
-
C.
Aeromar
Aeromar is a Mexican regional airline that primarily operates domestic and short-haul international flights, with a major operational base in Mexico City.
-
D.
Oceaneering International
Oceaneering International is a global engineering and technology company best known for its work in offshore energy services and advanced ride systems for major theme parks.
-
E.
Evergreen Marine
Evergreen Marine is a major Taiwanese container shipping company known for operating one of the world’s largest fleets of container vessels.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Atlantic Marine Triple: [RV Kilo Moana, builder, Atlantic Marine]
Generated description
Atlantic Marine is a shipbuilding company known for constructing specialized research and commercial vessels.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Atlantic Marine Target entity description: Atlantic Marine is a shipbuilding company known for constructing specialized research and commercial vessels.
-
A.
Jersey Marine
Jersey Marine is a coastal village in South Wales known for its proximity to Swansea Bay and its historic tower landmark.
-
B.
Caladan Oceanic
Caladan Oceanic is a private deep-sea exploration company known for organizing and conducting record-breaking manned expeditions to the deepest points in the world’s oceans.
-
C.
Aeromar
Aeromar is a Mexican regional airline that primarily operates domestic and short-haul international flights, with a major operational base in Mexico City.
-
D.
Oceaneering International
Oceaneering International is a global engineering and technology company best known for its work in offshore energy services and advanced ride systems for major theme parks.
-
E.
Evergreen Marine
Evergreen Marine is a major Taiwanese container shipping company known for operating one of the world’s largest fleets of container vessels.
- F. None of above. chosen
Provenance (5 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_69ad859b54f881909bf530d549caf2fd |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adaff74af88190809313743b439ff0 |
completed | March 8, 2026, 5:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b28f0a71d48190a5e673aed011f218 |
completed | March 12, 2026, 10:01 a.m. |
| NEDg | Description generation | batch_69b28fe1a32c8190a22e4218d23d12f1 |
completed | March 12, 2026, 10:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2a8ba4ee8819091b86fdf1369b3f8 |
completed | March 12, 2026, 11:51 a.m. |
Created at: March 8, 2026, 3:10 p.m.