Triple
T37339379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Bunker Hill |
E926987
|
entity |
| Predicate | sufferedAttackType |
P4333
|
FINISHED |
| Object | kamikaze attack |
—
|
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: kamikaze attack | Statement: [USS Bunker Hill, sufferedAttackType, kamikaze attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sufferedAttackType Context triple: [USS Bunker Hill, sufferedAttackType, kamikaze attack]
-
A.
attackType
chosen
Indicates the specific method, style, or category of attack used in an aggressive or hostile action between entities.
-
B.
wasAttackedIn
Indicates that an entity experienced an attack that occurred at or within a specified location or context.
-
C.
perpetratedAttackOn
Indicates that one entity carried out, organized, or was responsible for an attack directed against another entity.
-
D.
attackedIn
Indicates that one entity carried out an attack in the location, context, or time frame specified by another entity or value.
-
E.
survivorOfAttack
Indicates that one entity has lived through and remains alive after being subjected to an attack carried out by another entity.
- 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_69f76eb4e8a881908bd40da28f36fc7e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.