Triple
T6913283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhang Zuolin |
E159987
|
entity |
| Predicate | perpetratorOfKilling |
P74108
|
FINISHED |
| Object | officers of the Imperial Japanese Army Kwantung Army |
—
|
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: officers of the Imperial Japanese Army Kwantung Army | Statement: [Zhang Zuolin, perpetratorOfKilling, officers of the Imperial Japanese Army Kwantung Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perpetratorOfKilling Context triple: [Zhang Zuolin, perpetratorOfKilling, officers of the Imperial Japanese Army Kwantung Army]
-
A.
allegedToHaveKilled
Indicates that one entity is claimed or accused, but not proven, to have killed another entity.
-
B.
typeOfKilling
Indicates a specific manner, method, or category of killing that characterizes how the killing was carried out.
-
C.
massacrePerpetrators
Indicates that the subject is responsible for carrying out or participating in a massacre against the object.
-
D.
placeOfKilling
Indicates the location where a killing event took place.
-
E.
numberOfPerpetratorsKilled
Indicates the count of perpetrators who were killed in the context of the described event or incident.
- 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_69c6883ab1008190a07129ff06f625d9 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d9dbca6c819091d8b65e54ada5d9 |
completed | March 27, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b93d688190a297244ce81b67ac |
completed | March 27, 2026, 7:17 p.m. |
| PDg | Predicate description generation | batch_69c6d8c48ba48190b8d3aa7b8d22816b |
completed | March 27, 2026, 7:21 p.m. |
Created at: March 27, 2026, 2:25 p.m.