Triple
T34280715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York |
E879581
|
entity |
| Predicate | hadChiefJusticeOfSupremeCourt |
P2234
|
FINISHED |
| Object | Samuel Nelson |
—
|
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: Samuel Nelson | Statement: [New York, hadChiefJusticeOfSupremeCourt, Samuel Nelson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadChiefJusticeOfSupremeCourt Context triple: [New York, hadChiefJusticeOfSupremeCourt, Samuel Nelson]
-
A.
chiefJustice
chosen
Indicates that one entity serves as the chief justice (the highest-ranking judicial officer) of another entity, such as a court or jurisdiction.
-
B.
nominatedToSupremeCourtBy
Indicates that one entity formally selected or put forward another entity as a candidate for a position on the Supreme Court.
-
C.
succeededByAsChiefJustice
Indicates that one individual directly followed another in the role of Chief Justice.
-
D.
succeededInOfficeAsAssociateJusticeBy
Indicates that one associate justice left office and was subsequently replaced in that judicial position by another associate justice.
-
E.
chiefJusticeSinceYear
Indicates that an entity has held the position of chief justice starting from a specified year.
- 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_69f349b5f6648190b9420d94a4cd16e0 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71362f1448190985a80ce7af475cb |
completed | May 3, 2026, 9:20 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:57 a.m.