Triple
T13014273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tupolev Tu-330 |
E322503
|
entity |
| Predicate | cargoDeck |
P107832
|
FINISHED |
| Object | pressurized cargo hold |
—
|
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: pressurized cargo hold | Statement: [Tupolev Tu-330, cargoDeck, pressurized cargo hold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cargoDeck Context triple: [Tupolev Tu-330, cargoDeck, pressurized cargo hold]
-
A.
wellDeck
Indicates that one entity has a well deck feature or structure used for launching, recovering, or housing vessels or equipment.
-
B.
cargo
Indicates that one entity is the goods or load being transported, carried, or shipped by another entity.
-
C.
cargoSystem
Indicates a relationship where an entity is part of, managed by, or associated with a cargo-handling or cargo-management system.
-
D.
dockable
Indicates that one entity is capable of being securely connected or attached to another, typically in a way that allows them to function together as a unit.
-
E.
platformMate
Indicates that two entities are located on the same platform or share the same platform context at a given time.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97ecbb8f4819094d55eb07cb5ad97 |
completed | April 10, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69d97dc153a081909d13a694993f074a |
completed | April 10, 2026, 10:46 p.m. |
| PDg | Predicate description generation | batch_69d97e74283c819082e69ac3554fa7d8 |
completed | April 10, 2026, 10:49 p.m. |
Created at: April 9, 2026, 8:50 p.m.