Triple
T23303353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Destroyer Squadron 4 |
E590364
|
entity |
| Predicate | commandShip |
P44211
|
FINISHED |
| Object | Japanese cruiser Nagara |
—
|
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: Japanese cruiser Nagara | Statement: [Destroyer Squadron 4, commandShip, Japanese cruiser Nagara]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commandShip Context triple: [Destroyer Squadron 4, commandShip, Japanese cruiser Nagara]
-
A.
commandsShip
chosen
Indicates that one entity has authority over and directs the operation of a ship.
-
B.
commandedFromShip
Indicates that an entity exercised command or control over something while located on or operating from a ship.
-
C.
organizedShip
Indicates that an entity arranged, managed, or coordinated the operation or voyage of a ship.
-
D.
componentShip
Indicates that one entity is a physical or logical component or part of another entity, such that the whole is composed of or depends on that component.
-
E.
shipFunction
Indicates that one entity serves as the functional role, purpose, or operational use of a ship.
- 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19724de488190ac8eb89253c8dd53 |
completed | April 29, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:04 p.m.