Triple
T31004947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tobin tax |
E790040
|
entity |
| Predicate | isUsuallyCollectedAt |
P94503
|
FINISHED |
| Object | point of foreign exchange transaction |
—
|
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: point of foreign exchange transaction | Statement: [Tobin tax, isUsuallyCollectedAt, point of foreign exchange transaction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isUsuallyCollectedAt Context triple: [Tobin tax, isUsuallyCollectedAt, point of foreign exchange transaction]
-
A.
collectedAtStation
chosen
Indicates that something was gathered, received, or picked up at a particular station location.
-
B.
canCollect
Indicates that one entity has the ability or permission to gather, receive, or take possession of another entity.
-
C.
collectedWith
Indicates that one entity was gathered, acquired, or obtained together with another entity as part of the same collection event or process.
-
D.
collectedAs
Indicates that one entity has been gathered, acquired, or assembled as part of another entity, such as a collection, set, or group.
-
E.
collectedThrough
Indicates that something was obtained, gathered, or acquired by means of a specified process, method, or channel.
- 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_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69f690ef92308190903a54fc74233269 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:57 p.m.