Triple
T18120414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ARP |
E433715
|
entity |
| Predicate | usedMeasure |
P1459
|
FINISHED |
| Object | blackout regulations |
—
|
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: blackout regulations | Statement: [ARP, usedMeasure, blackout regulations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedMeasure Context triple: [ARP, usedMeasure, blackout regulations]
-
A.
containsMeasure
Indicates that one entity includes or encompasses a specific measure or quantitative component as part of its content or structure.
-
B.
wasPreviouslyMeasuredAs
Indicates that an entity had a specific measurement or value at an earlier time, which may differ from its current measurement.
-
C.
usesMetric
chosen
Indicates that one entity adopts, applies, or relies on a particular metric or measurement standard in its operation, evaluation, or description.
-
D.
measured
Indicates that one entity has determined or quantified a property, amount, or extent of another entity using some standard or instrument.
-
E.
measuredAs
Indicates that one entity’s quantity, value, or property is expressed or recorded using another entity as its measurement or unit.
- 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_69d8b909e8cc81908df4cc2b8ea6d11f |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddd9b21c81908d23b8d9840410df |
completed | April 19, 2026, 1:51 p.m. |
| PD | Predicate disambiguation | batch_69e43313ca788190baa224269e71de49 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:28 a.m.