Triple
T700956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Federal Rules of Civil Procedure |
E13996
|
entity |
| Predicate | 2007RevisionType |
P17936
|
FINISHED |
| Object | restyling for clarity |
—
|
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: restyling for clarity | Statement: [United States Federal Rules of Civil Procedure, 2007RevisionType, restyling for clarity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 2007RevisionType Context triple: [United States Federal Rules of Civil Procedure, 2007RevisionType, restyling for clarity]
-
A.
revisionMechanism
Indicates the method or process by which something is updated, corrected, or modified over time.
-
B.
revisionKnownAs
Indicates that a particular revision of an entity is referred to or identified by a specific alternative name or label.
-
C.
typeOfAmendment
chosen
Indicates the specific kind or category of amendment that is being applied to something, such as a document, law, or agreement.
-
D.
significantRevisionIn
Indicates that one entity represents a substantial or important change made within another entity, such as a major update or revision occurring in a larger work or version.
-
E.
reversionYear
Indicates the year in which something returns to a previous state, condition, or ownership.
- 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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a544e3608190ac315c7aa9f88e7e |
completed | March 1, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_69a4a4ec8c748190b198492a0eea4445 |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:36 p.m.