Triple
T125389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dallas Reports |
E2535
|
entity |
| Predicate | lastVolumeNumberInUSReports |
P3130
|
FINISHED |
| Object | 4 U.S. |
—
|
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: 4 U.S. | Statement: [Dallas Reports, lastVolumeNumberInUSReports, 4 U.S.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastVolumeNumberInUSReports Context triple: [Dallas Reports, lastVolumeNumberInUSReports, 4 U.S.]
-
A.
volumeInUnitedStatesReports
chosen
Indicates that a legal case or decision is published in a specified volume of the United States Reports.
-
B.
numberOfVolumes
Indicates the total count of separate volumes or parts that make up a multi-volume work or collection.
-
C.
editionNumber
Indicates the specific sequential number assigned to an edition of a work within its series of published versions.
-
D.
lastLifetimeEditionYear
Indicates the year in which the most recent lifetime edition of an entity (such as a work or product) was issued or became available.
-
E.
officiallyReports
Indicates that one entity formally provides information, updates, or accountability to another entity within an official or authorized reporting structure.
- 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_69a251b54ea88190b18281669f59b4c0 |
completed | Feb. 28, 2026, 2:23 a.m. |
| NER | Named-entity recognition | batch_69a2573e4e6481908252dfef2e34f46e |
completed | Feb. 28, 2026, 2:47 a.m. |
| PD | Predicate disambiguation | batch_69a2564a54948190ba30bee858173b27 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:27 a.m.