Triple
T60823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States courts of appeals |
E1207
|
entity |
| Predicate | judgesTerm |
P4505
|
FINISHED |
| Object | during good behavior |
—
|
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: during good behavior | Statement: [United States courts of appeals, judgesTerm, during good behavior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: judgesTerm Context triple: [United States courts of appeals, judgesTerm, during good behavior]
-
A.
numberOfJudges
Indicates the total count of judges associated with a particular case, event, or entity.
-
B.
judge
Indicates that one entity evaluates, forms an opinion about, or makes a decision regarding another entity or situation.
-
C.
bindingNatureOfJudgments
Indicates that judgments or decisions have a compulsory, legally enforceable effect on the parties or entities to which they apply.
-
D.
judicialBody
Indicates that an entity serves as a court or tribunal with authority to adjudicate legal disputes or interpret and apply the law.
-
E.
decidesOn
Indicates that an agent makes a choice or determination regarding a particular option, issue, or course of action.
- F. None of above. chosen
Provenance (4 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_69a24ba4f760819081f6638a3c70538a |
completed | Feb. 28, 2026, 1:57 a.m. |
| NER | Named-entity recognition | batch_69a251a1b8ac8190b44be4c3c41e5681 |
completed | Feb. 28, 2026, 2:23 a.m. |
| PD | Predicate disambiguation | batch_69a24ea0bec48190b2af1fb287e9e692 |
completed | Feb. 28, 2026, 2:10 a.m. |
| PDg | Predicate description generation | batch_69a251a088f8819083797c2baf310c39 |
completed | Feb. 28, 2026, 2:23 a.m. |
Created at: Feb. 28, 2026, 2:02 a.m.