Triple
T2090531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Court of Claims |
E32657
|
entity |
| Predicate | judicialSelectionType |
P11399
|
FINISHED |
| Object | appointment |
—
|
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: appointment | Statement: [New York Court of Claims, judicialSelectionType, appointment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: judicialSelectionType Context triple: [New York Court of Claims, judicialSelectionType, appointment]
-
A.
justicesSelectedFrom
Indicates that certain justices are chosen or appointed from a particular group, body, or pool of candidates.
-
B.
judicialRole
Indicates that one entity holds or performs a specific official function or position within the judicial system in relation to another entity or legal matter.
-
C.
hasJudiciary
Indicates that an entity possesses, is served by, or is under the authority of a judicial body or legal court system.
-
D.
presidencySelection
Indicates the process or outcome by which an individual is chosen or appointed to hold the office of the presidency.
-
E.
appointedOrElected
chosen
Indicates that an entity attained a position, role, or office through either an appointment process or an electoral process.
- 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_69a885eba0708190999696a45cbec816 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abba7443448190a2642769d0b5fb93 |
completed | March 7, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69abb7b4356881909217c42ccb8bb1ed |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.