Triple
T1516345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanjing War Crimes Tribunal |
E32127
|
entity |
| Predicate | defendantsNationality |
P29967
|
FINISHED |
| Object | Japanese |
—
|
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 | Statement: [Nanjing War Crimes Tribunal, defendantsNationality, Japanese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defendantsNationality Context triple: [Nanjing War Crimes Tribunal, defendantsNationality, Japanese]
-
A.
hasVictimNationalities
Indicates that an event, incident, or action involved victims belonging to one or more specified nationalities.
-
B.
countryOfJurisdiction
Indicates the country whose legal authority or jurisdiction governs or applies to a given entity, action, or arrangement.
-
C.
nationalityRepresented
Indicates the country or nation that an entity officially represents, typically in a professional, competitive, or diplomatic capacity.
-
D.
legalOrigin
Indicates the foundational legal system or jurisdiction from which an entity’s laws, regulations, or legal framework are derived.
-
E.
nationalityInText
Indicates that a person's nationality is mentioned or specified within a given text.
- 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_69a885e8caf88190a5fbb6159ce87786 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9396e16408190b5e7b0ac43376d81 |
completed | March 5, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69a907aa67cc81909f00135365447399 |
completed | March 5, 2026, 4:33 a.m. |
| PDg | Predicate description generation | batch_69a9396d3e1081909aa269b42041c357 |
completed | March 5, 2026, 8:06 a.m. |
Created at: March 4, 2026, 7:26 p.m.