Triple
T193691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Economic Conference |
E3772
|
entity |
| Predicate | wasUnderminedBy |
P993
|
FINISHED |
| Object | United States withdrawal from currency stabilization talks |
—
|
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: United States withdrawal from currency stabilization talks | Statement: [London Economic Conference, wasUnderminedBy, United States withdrawal from currency stabilization talks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasUnderminedBy Context triple: [London Economic Conference, wasUnderminedBy, United States withdrawal from currency stabilization talks]
-
A.
wasSupersededBy
Indicates that one entity has been replaced or made obsolete by another entity that takes over its role or function.
-
B.
wasOverturnedByCourt
Indicates that a prior decision, ruling, or judgment was reversed or nullified by a court.
-
C.
damagedBy
chosen
Indicates that one entity has caused harm, impairment, or deterioration to another entity.
-
D.
opposedBy
Indicates that one entity actively resists, disagrees with, or works against the actions, views, or position of another entity.
-
E.
defeatedCandidate
Indicates that one candidate has won an election or contest against another candidate, causing the other to lose.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a2596810c48190ab687c0c2efaa9e2 |
completed | Feb. 28, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69a256769ad8819083c1d83082c0215e |
completed | Feb. 28, 2026, 2:44 a.m. |
Created at: Feb. 28, 2026, 2:41 a.m.