Triple
T28765318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS New Zealand |
E726250
|
entity |
| Predicate | damageAtJutland |
P822
|
FINISHED |
| Object | hit by several shells but remained operational |
—
|
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: hit by several shells but remained operational | Statement: [HMS New Zealand, damageAtJutland, hit by several shells but remained operational]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: damageAtJutland Context triple: [HMS New Zealand, damageAtJutland, hit by several shells but remained operational]
-
A.
enemyEngagementAtJutland
Indicates that an entity participated in or was involved in hostile military action against an enemy during the Battle of Jutland.
-
B.
survivorsAtJutland
Indicates that the entities were survivors of the Battle of Jutland.
-
C.
battleshipsDamaged
chosen
Indicates that one or more battleships have sustained damage, typically as a result of combat or hostile action.
-
D.
battleOfJutlandDate
Indicates the specific calendar date on which the Battle of Jutland took place.
-
E.
warDamage
Indicates damage that was caused as a direct consequence of war or armed conflict.
- 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_69f03198be14819098fa74e48b3749bf |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658ee40088190b71e1219407690d0 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:13 a.m.