Triple
T20174075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | truth in advertising |
E492042
|
entity |
| Predicate | mayBeBackedBy |
P131256
|
FINISHED |
| Object | civil penalties |
—
|
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: civil penalties | Statement: [truth in advertising, mayBeBackedBy, civil penalties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayBeBackedBy Context triple: [truth in advertising, mayBeBackedBy, civil penalties]
-
A.
canBeBackedBy
chosen
Indicates that one entity is capable of being supported, guaranteed, or secured by another entity.
-
B.
backedFor
Indicates that one entity provides support, endorsement, or backing for another entity, often in a financial, political, or strategic context.
-
C.
backedByMechanism
Indicates that something is supported, enabled, or made possible by an underlying mechanism or system.
-
D.
canBePulledBackAlong
Indicates that a structure or object can be transferred or redefined along a given mapping or morphism so that it is compatible with that mapping.
-
E.
mayHaveSupported
Indicates that an entity possibly provided assistance, endorsement, or backing to another entity, without asserting that this support definitely occurred.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6684a33688190b22cfc16907e76bc |
completed | April 20, 2026, 5:54 p.m. |
| PD | Predicate disambiguation | batch_69e55b0c11cc8190836d1eee5945f000 |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:36 p.m.