Triple
T738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States of America |
E14
|
entity |
| Predicate | drivesOn |
P246
|
FINISHED |
| Object | right |
—
|
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: right | Statement: [United States of America, drivesOn, right]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drivesOn Context triple: [United States of America, drivesOn, right]
-
A.
operatesBy
Indicates that an entity performs its function, action, or process through the use or application of another entity (e.g., a method, mechanism, or principle).
-
B.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
C.
hasPart
Indicates that one entity is a component, segment, or constituent part of another entity.
-
D.
requires
Indicates that one entity must exist, occur, or be satisfied before another entity can exist, occur, or be carried out.
-
E.
isMechanicalOrElectronic
Indicates that something operates using mechanical components, electronic components, or a combination of both.
- F. None of above. chosen
Provenance (4 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a23211f05c8190b8deb03a8540d84d |
completed | Feb. 28, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69a230c2c48481908beb1db3cc9768aa |
completed | Feb. 28, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69a23211181c81909c2db8796d2aded4 |
completed | Feb. 28, 2026, 12:08 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.