Triple
T37119132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS St. Lo |
E919198
|
entity |
| Predicate | kamikazeAttacker |
P187167
|
FINISHED |
| Object | Japanese Yokosuka D4Y dive bomber |
—
|
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: Japanese Yokosuka D4Y dive bomber | Statement: [USS St. Lo, kamikazeAttacker, Japanese Yokosuka D4Y dive bomber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: kamikazeAttacker Context triple: [USS St. Lo, kamikazeAttacker, Japanese Yokosuka D4Y dive bomber]
-
A.
kamikazeHits
Indicates that an attacking entity deliberately crashes into and strikes a target in a suicidal or self-destructive manner.
-
B.
JapaneseAirCommander
Indicates that one entity serves as a Japanese air force commander in relation to another entity or context.
-
C.
operationalCommanderAttacker
Indicates that the subject serves as the operational commander directing and controlling the attacking forces in the described action or event.
-
D.
airGroupCommanderAttacker
Indicates that the subject serves as the commanding officer of an air group that is carrying out an attack.
-
E.
commanderAttacker
Indicates that one entity serves as the commanding officer or leader of another entity that is acting as the attacker in a conflict or operation.
- F. None of above. chosen
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_69f76e9c57148190ba789dd059645bb9 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
| PDg | Predicate description generation | batch_69fb344ba5408190a6fe8face293d88b |
completed | May 6, 2026, 12:30 p.m. |
Created at: May 3, 2026, 4:15 p.m.