Triple
T29112144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Hong |
E736939
|
entity |
| Predicate | causeOfUnrest |
P107944
|
FINISHED |
| Object | sale of offices and heavy taxation |
—
|
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: sale of offices and heavy taxation | Statement: [Liu Hong, causeOfUnrest, sale of offices and heavy taxation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfUnrest Context triple: [Liu Hong, causeOfUnrest, sale of offices and heavy taxation]
-
A.
causeOfPoliticalConflict
Indicates that one entity is the source or reason for a political conflict involving another entity.
-
B.
motiveForUprising
chosen
Indicates that a particular factor, condition, or event serves as a motivating cause or justification for an uprising or rebellion.
-
C.
hasCauseOfConflict
Indicates a relationship where one entity is the source or reason for a conflict involving another entity.
-
D.
societalConflict
Indicates a relationship where groups or individuals within a society are in opposition or tension over values, resources, power, or social norms.
-
E.
endCauseOfRevolt
Indicates that the subject is the cause or factor that brings a revolt or uprising to an end.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f71f8ee0688190bd025f27993452d3 |
completed | May 3, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_69f71cc405c08190863565609a4c8499 |
completed | May 3, 2026, 10 a.m. |
Created at: April 28, 2026, 11:19 a.m.