Triple
T31004949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tobin tax |
E790040
|
entity |
| Predicate | isPartOfDebateOn |
P49860
|
FINISHED |
| Object | regulation of global capital flows |
—
|
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: regulation of global capital flows | Statement: [Tobin tax, isPartOfDebateOn, regulation of global capital flows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfDebateOn Context triple: [Tobin tax, isPartOfDebateOn, regulation of global capital flows]
-
A.
partOfDebate
chosen
Indicates that one entity is a component, segment, or participant within a larger debate or argumentative exchange.
-
B.
hasDebateAround
Indicates that there is ongoing discussion, disagreement, or controversy surrounding the referenced entity or topic.
-
C.
debatedWithin
Indicates that something is discussed or argued about within a particular group, context, or domain.
-
D.
debatedAs
Indicates that one entity is discussed or argued over in terms of being equivalent to, or serving in the role of, another entity within a debate or comparative argument.
-
E.
hasDebate
Indicates that there is a formal discussion or argument between entities, typically presenting opposing viewpoints on a topic.
- 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_69f224c73ca48190a1e46cb58ad4045b |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe349879848190bcd77e3cc3470458 |
completed | May 8, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69fe31e3cf908190b23ebc2f7fe58722 |
completed | May 8, 2026, 6:56 p.m. |
Created at: April 29, 2026, 8:57 p.m.