Triple
T7413714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levi P. Morton |
E171074
|
entity |
| Predicate | precededInOfficeAsGovernorOfNewYorkBy |
P60263
|
FINISHED |
| Object | Roswell P. Flower |
—
|
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: Roswell P. Flower | Statement: [Levi P. Morton, precededInOfficeAsGovernorOfNewYorkBy, Roswell P. Flower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precededInOfficeAsGovernorOfNewYorkBy Context triple: [Levi P. Morton, precededInOfficeAsGovernorOfNewYorkBy, Roswell P. Flower]
-
A.
succeededBy (Governor of New York)
Indicates that one individual directly follows another in holding the office of Governor of New York.
-
B.
precededBy (Governor of New York)
chosen
Indicates that one entity held the position of Governor of New York before another entity.
-
C.
precededInOfficeAsSenatorFromNewYorkBy
Indicates that one individual assumed the role of U.S. Senator from New York after another, who directly held the office immediately before them.
-
D.
laterGovernor
Indicates that one entity subsequently became the governor of a place or jurisdiction associated with another entity.
-
E.
precededInOfficeAsGovernorOfGeorgiaBy
Indicates that one individual assumed the office of Governor of Georgia after another specific individual, who directly held the position immediately before them.
- 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_69c68a618bdc81908d8018edadecd1a4 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f2c336308190932c14cec5eec25f |
completed | March 27, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69c6f0345040819094c5756dfa487faf |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:11 p.m.