Triple
T3967687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese battleship Mikasa |
E92254
|
entity |
| Predicate | serviceAfterRepair |
P4690
|
FINISHED |
| Object | training and coastal defense duties |
—
|
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: training and coastal defense duties | Statement: [Japanese battleship Mikasa, serviceAfterRepair, training and coastal defense duties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceAfterRepair Context triple: [Japanese battleship Mikasa, serviceAfterRepair, training and coastal defense duties]
-
A.
serviceDuring
Indicates that one entity performs or provides a service for another entity during a specified time period or event.
-
B.
service
chosen
Indicates that one entity performs work, assistance, or functions to meet the needs or requests of another entity.
-
C.
repairedIn
Indicates that an item or object underwent repair within a specified location or during a particular time period.
-
D.
serviceWith
Indicates that one entity provides or is associated with a particular service offered to or used by another entity.
-
E.
useAfterRenovation
Indicates that something is intended to be used or occupied only after renovation work has been completed.
- 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_69aed96624188190ac8c45bb57ab72b5 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefaca33e4819091957c7915857a42 |
completed | March 9, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69aef8f252b081909749d40440d372b2 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:32 p.m.