Triple
T11752591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Doe |
E279442
|
entity |
| Predicate | associatedWithAreaOfLaw |
P62104
|
FINISHED |
| Object | constitutional law |
—
|
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: constitutional law | Statement: [John Doe, associatedWithAreaOfLaw, constitutional law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithAreaOfLaw Context triple: [John Doe, associatedWithAreaOfLaw, constitutional law]
-
A.
associatedWithJurisdiction
Indicates that an entity has a formal or relevant connection to a particular legal or administrative jurisdiction.
-
B.
notableAreaOfLaw
chosen
Indicates that a person or entity is particularly recognized or distinguished in a specific field or area of law.
-
C.
relatedCaseArea
Indicates that one case is associated with, pertains to, or falls within the subject matter or domain of another case area.
-
D.
associatedWithCourt
Indicates a relationship in which an entity is linked or connected to a specific court, such as through jurisdiction, affiliation, or involvement in legal proceedings.
-
E.
branchOfLaw
Indicates a relationship where one legal field or discipline is a subdivision or specialized area within a broader body of law.
- 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a509c2448190b0deb7ed29c3a73f |
completed | April 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69d88a813cc48190a3dfdc60e8af80ae |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.