Triple
T29641892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Union Treaty |
E755883
|
entity |
| Predicate | wouldTransformEntity |
P165796
|
FINISHED |
| Object | Union of Soviet Socialist Republics |
—
|
NE NERFINISHED |
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: Union of Soviet Socialist Republics | Statement: [New Union Treaty, wouldTransformEntity, Union of Soviet Socialist Republics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wouldTransformEntity Context triple: [New Union Treaty, wouldTransformEntity, Union of Soviet Socialist Republics]
-
A.
wouldTransform
chosen
Indicates that one entity has the potential or hypothetical effect of changing, converting, or altering another entity into a different state or form.
-
B.
canTransform
Indicates that one entity is capable of being changed or converted into another entity or state.
-
C.
usesTransformation
Indicates that one entity applies or relies on a specific transformation process, method, or function to operate on or convert another entity.
-
D.
includesTransformation
Indicates that one entity’s process, definition, or composition contains or involves a transformation applied to another entity.
-
E.
attemptsToTransform
Indicates an entity’s effort or action aimed at changing or converting another entity from one state, form, or condition to another.
- 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_69f0ef89d2c88190a6d0d5116ccd7cc9 |
completed | April 28, 2026, 5:34 p.m. |
| NER | Named-entity recognition | batch_69f66ed0653c819085adda918bd12f83 |
completed | May 2, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 6:47 p.m.