Triple
T29093314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parker v. District of Columbia (2007) |
E734919
|
entity |
| Predicate | hasPanelJudge |
P19462
|
FINISHED |
| Object | Laurence H. Silberman |
—
|
NE NERFINISHED |
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: Laurence H. Silberman | Statement: [Parker v. District of Columbia (2007), hasPanelJudge, Laurence H. Silberman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPanelJudge Context triple: [Parker v. District of Columbia (2007), hasPanelJudge, Laurence H. Silberman]
-
A.
hasJudges
Indicates that one entity serves as a judge or panel of judges for another entity, such as an event, competition, or legal case.
-
B.
hasJudge
chosen
Indicates that a legal case, proceeding, or decision is presided over or decided by a particular judge.
-
C.
hasJudgeFrom
Indicates that an entity has a judge whose origin, affiliation, or source is from a specified place or organization.
-
D.
hasJudgesRole
Indicates that an entity serves in the capacity or role of a judge within a specified context or system.
-
E.
hasPanel
Indicates that one entity includes, is equipped with, or is associated with a panel as a component or feature.
- 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_69f05b0ed66481908f2e864fa550d2f1 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fd49f6dbac81909744373a357b7982 |
completed | May 8, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69fd48ed68f481908374183c66a6b055 |
completed | May 8, 2026, 2:22 a.m. |
Created at: April 28, 2026, 11:06 a.m.