Triple
T9178232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial Japanese Navy submarine I-19 |
E220254
|
entity |
| Predicate | locationOfNotableAttack |
P20435
|
FINISHED |
| Object | south of Guadalcanal |
—
|
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: south of Guadalcanal | Statement: [Imperial Japanese Navy submarine I-19, locationOfNotableAttack, south of Guadalcanal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfNotableAttack Context triple: [Imperial Japanese Navy submarine I-19, locationOfNotableAttack, south of Guadalcanal]
-
A.
notableAttackLocation
chosen
Indicates the specific place where a significant or notable attack occurred in relation to the subject.
-
B.
locationOfAttacksCondemned
Indicates that a specific location is the site of attacks that have been explicitly denounced or condemned.
-
C.
notableAttack
Indicates that an entity carried out, was involved in, or is strongly associated with a particularly significant or well-known attack.
-
D.
bombingLocation
Indicates the place where a bombing event occurs or is carried out.
-
E.
attackedIn
Indicates that one entity carried out an attack in the location, context, or time frame specified by another entity or value.
- 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_69ca83e589948190ac9907819db11ddf |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccc24eeb988190af82dfba49aac2f8 |
completed | April 1, 2026, 6:59 a.m. |
| PD | Predicate disambiguation | batch_69cc660761d88190ab6134b43b376964 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:23 p.m.