Triple
T33617145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cruiser Division 6 |
E861148
|
entity |
| Predicate | includedVessel |
P110548
|
FINISHED |
| Object | Japanese cruiser Aoba |
E76917
|
NE 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: Japanese cruiser Aoba | Statement: [Cruiser Division 6, includedVessel, Japanese cruiser Aoba]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includedVessel Context triple: [Cruiser Division 6, includedVessel, Japanese cruiser Aoba]
-
A.
hasVessel
Indicates that one entity possesses, uses, or is associated with a particular vessel (such as a container, ship, or transport medium) in the context of the described relationship or action.
-
B.
isVesselFor
Indicates that one entity functions as a container or medium specifically used to hold, carry, or convey another entity.
-
C.
namedVesselOf
chosen
Indicates that one entity is the specific named vessel (e.g., ship, boat, or craft) associated with or belonging to another entity.
-
D.
usesVesselType
Indicates that an entity performs an activity or operation by employing a specific type or category of vessel.
-
E.
hasVesselType
Indicates that an entity is associated with or classified by a specific type of vessel (e.g., ship, boat, or container).
- F. None of above.
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_69f34980fabc81909819228729a9ca84 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a03352bb9688190b965d188769fcacd |
completed | May 12, 2026, 2:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a368221adf08190ba48ee1d602009c1 |
completed | June 20, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_6a033329ae5c81909532843fe716ec77 |
completed | May 12, 2026, 2:03 p.m. |
Created at: May 1, 2026, 1:41 a.m.