Triple
T16941816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | dangwai movement |
E410965
|
entity |
| Predicate | wasIllegalUnder |
P20780
|
FINISHED |
| Object | martial law in Taiwan |
—
|
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: martial law in Taiwan | Statement: [dangwai movement, wasIllegalUnder, martial law in Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasIllegalUnder Context triple: [dangwai movement, wasIllegalUnder, martial law in Taiwan]
-
A.
hasNoLegalAuthority
Indicates that an entity lacks the official power, right, or authorization to perform a specified action or make binding decisions in a given context.
-
B.
wasOnceOutlawed
Indicates that an entity was previously considered illegal or banned by an authority but is no longer outlawed.
-
C.
legality
Indicates that an action, object, or situation conforms to, violates, or is evaluated in terms of formal laws or legal rules.
-
D.
declaredIllegalIn
chosen
Indicates that an authority has officially designated something as illegal within a specific jurisdiction or context.
-
E.
foundUnlawfulBy
Indicates that an entity has been judged or determined to have acted unlawfully by a particular authority or decision-making body.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cfadec70819095ec0048ebc71016 |
completed | April 18, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_69e32b9aa8748190b248890aca86753d |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:31 a.m.